frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

Refresh SkillOps evidence reports

Browse Source
This commit is contained in:
yaojingang
2026-06-16 04:48:33 +08:00
parent 3677dd4664
commit 904969b91f
68 changed files with 1214 additions and 853 deletions
Download Patch File Download Diff File Expand all files Collapse all files
registry/index.json
+2 -2
View File
@@ -1,6 +1,6 @@
{
"schema_version": "2.0",
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"package_count": 1,
"packages": [
{
@@ -16,7 +16,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083"
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7"
}
]
}
registry/packages/yao-meta-skill.json
+4 -4
View File
@@ -16,8 +16,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed"
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35"
},
"compatibility": {
"openai": "pass",
@@ -48,10 +48,10 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-13"
"generated_at": "2026-06-16"
}
reports/adaptation_proposals.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16",
"generated_at": "2026-06-15T20:47:47Z",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
reports/adaptation_proposals.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Adaptation Proposals
- Generated at: `2026-06-16`
- Generated at: `2026-06-15T20:47:47Z`
- Pattern report: `reports/user_patterns.json`
- Proposal only: `true`
- Writes repository files: `false`
reports/adoption_drift_report.json
+14 -14
View File
@@ -1,7 +1,7 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-15T20:34:53Z",
"generated_at": "2026-06-15T20:47:47Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
@@ -25,14 +25,14 @@
},
"summary": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"edited_count": 0,
"rejected_count": 0,
"missed_count": 0,
"failed_count": 0,
"adoption_rate": 100.0,
"adoption_rate": 0,
"missed_trigger_count": 0,
"wrong_trigger_count": 0,
"bad_output_count": 0,
@@ -41,7 +41,7 @@
"review_overdue_count": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"failure_types": {},
"source_types": {
@@ -53,31 +53,31 @@
{
"skill": "yao-meta-skill",
"events": 1,
"adoption_events": 1,
"accepted": 1,
"adoption_events": 0,
"accepted": 0,
"edited": 0,
"rejected": 0,
"missed": 0,
"adoption_rate": 100.0
"adoption_rate": 0
}
],
"next_iteration_candidates": [],
"recent_events": [
{
"command": "unknown",
"event": "skill_activation",
"event": "review_event",
"skill": "yao-meta-skill",
"source": "manual",
"version": "1.1.0",
"activation_type": "explicit",
"outcome": "accepted",
"activation_type": "manual",
"outcome": "reviewed",
"failure_type": "none",
"timestamp": "2026-06-13T10:00:00Z"
"timestamp": "2026-06-13T12:00:00Z"
}
],
"failures": [],
"artifacts": {
"events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl",
"events_jsonl": "reports/telemetry_events.jsonl",
"json": "reports/adoption_drift_report.json",
"markdown": "reports/adoption_drift_report.md"
}
reports/adoption_drift_report.md
+5 -5
View File
@@ -5,9 +5,9 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
## Summary
- Events: `1`
- Adoption samples: `1`
- Activation events: `1`
- Adoption rate: `100.0`
- Adoption samples: `0`
- Activation events: `0`
- Adoption rate: `0`
- Missed trigger signals: `0`
- Bad output signals: `0`
- Script error signals: `0`
@@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
| Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 |
| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 |
## Next Iteration Candidates
@@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
## Recent Metadata Events
- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none`
- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none`
reports/architecture_maintainability.json
+5 -5
View File
@@ -1,13 +1,13 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"python_file_count": 181,
"script_file_count": 115,
"test_file_count": 66,
"internal_module_count": 34,
"python_file_count": 183,
"script_file_count": 116,
"test_file_count": 67,
"internal_module_count": 35,
"cli_script_count": 83,
"command_handler_count": 66,
"entrypoint_command_handler_count": 18,
reports/architecture_maintainability.md
+5 -5
View File
@@ -1,14 +1,14 @@
# Architecture Maintainability
Generated at: `2026-06-13`
Generated at: `2026-06-16`
## Summary
- decision: `pass`
- python files: `181`
- scripts: `115`
- tests: `66`
- internal modules: `34`
- python files: `183`
- scripts: `116`
- tests: `67`
- internal modules: `35`
- CLI scripts: `83`
- Yao CLI command handlers: `66`
- entrypoint command handlers: `18`
reports/benchmark_reproducibility.json
+56 -42
View File
@@ -3,23 +3,36 @@
"ok": true,
"generated_at": "2026-06-16",
"skill_dir": ".",
"commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0",
"commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 69,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.json",
" M reports/adoption_drift_report.md",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/compiled_targets.json",
" M reports/context_budget.json"
],
"scope": "generation-time status before this report is written"
},
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4",
"source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"evidence_bundle_sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c",
"source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -34,29 +47,30 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
"world_class_source_blocked_count": 6,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 69
},
"public_claim": {
"ready": false,
"scope": "public benchmark or world-class readiness claim",
"blockers": [
"release lock is not clean or commit is unavailable",
"provider-backed model holdout evidence is incomplete",
"human blind-review adjudication is incomplete",
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
"world-class source checks are not all accepted (7/13 pass, 6 blocked)"
"world-class source checks are not all accepted (6/13 pass, 7 blocked)"
],
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
},
"release_lock": {
"ready": true,
"commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0",
"ready": false,
"commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5",
"status_scope": "generation-time status before this report is written",
"reason": "clean generation-time HEAD"
"reason": "working tree was dirty at generation time"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -64,7 +78,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4"
"sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -137,8 +151,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "f9487c444b2f9dfba3ce0dd9d22a828c23d9a52d772a9017265ca898c9ef2b75"
"bytes": 7967,
"sha256": "c1f94258e640e449eca383be009ff54d883f44bace9738d7717392043b1d3e71"
},
{
"label": "blind_review",
@@ -172,64 +186,64 @@
"label": "trust_report",
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 113207,
"sha256": "ba3b69b8eb33e907fb14a4e86c70bc6dd05d666baa6b8dbce787a03a156663a7"
"bytes": 113805,
"sha256": "47c789ac5ff9404eaeb16fa762a805ea8d12c923dd54c74f97d1f3ccb312a556"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 23905,
"sha256": "01aa970d0d213f0561787dbae628cc92df9085e1c5fb57f62ecae9cfabceae31"
"bytes": 24156,
"sha256": "9392cf6f3c9042044ddd5e2467e4e81f7d9e31587265d906359d4ca80c9e0958"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "979fb0ac2207d6cf8cb41ec68fd13da8007f0033cf29b07404cfae1d1c20b9d8"
"sha256": "462d39d38d11e4f885ba965a320a61dbf0d4ad9b8bd6fe909ee0c039b3058f08"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "e46eaa920aca5a6394897610f743372bcc3e81fc17f1e3cd9eb552ddb6ed4945"
"sha256": "bd6b8467def56d3667aa931c5ace75227dc9f4345e0ab02632d1d99e5aeac91a"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8758,
"sha256": "4d071571c537ad2f43d3f1c8ad3a0928417ec9d9137a704f2baec95e5a2307a2"
"bytes": 8604,
"sha256": "1ad04c50c23ff7c76115b7218d22c4c86ea10bf2bcefb34d4b2d6d10122f350b"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "f881e979b36e4d98cf7b737589e39d308568e033ecc8d5125a964c64b70683ec"
"sha256": "e7d9819e12a79f97a0e708f6401db7ede878deff3a9b2aa3fe2f5aba09fdb15e"
},
{
"label": "world_class_evidence_plan",
"path": "reports/world_class_evidence_plan.json",
"exists": true,
"bytes": 19940,
"sha256": "b408af112c784fdc3e96ea9ecf374990b9f58a0ebfa4df18394ccd9e93dc5545"
"sha256": "76a3f8e2b12b9ace575f3465bcee7697ddffb3440eed7ca3c3bb0becc61e1ab7"
},
{
"label": "world_class_evidence_ledger",
"path": "reports/world_class_evidence_ledger.json",
"exists": true,
"bytes": 21277,
"sha256": "63d7aaedf72503c21577928da46783e0ec55b0e92af326cb92ab1e01289db9f5"
"bytes": 21280,
"sha256": "1cb74eaa978b8a4aee3a95c4459bffb4092f2de8476fd18acce4b943687481b6"
},
{
"label": "world_class_evidence_intake",
"path": "reports/world_class_evidence_intake.json",
"exists": true,
"bytes": 18865,
"sha256": "2fbecc603d8dc6382fde6c61869aaf4b56fc9d1be5afcd07b345c419dce6d55a"
"sha256": "99a0ba234d59c0329d4645064bd67508c3057cbcc684016437bd0c7f4d9c3b2a"
},
{
"label": "world_class_evidence_preflight",
@@ -242,36 +256,36 @@
"label": "world_class_submission_review",
"path": "reports/world_class_submission_review.json",
"exists": true,
"bytes": 13550,
"sha256": "ab20b288f47f2a739ec7862fa8a04985584a729d588a32dca3d71ba64d8de2fc"
"bytes": 13553,
"sha256": "b8317119e9cd19044bac24f9ff5f5ea7def5f7c782b0bb93b9ba4aa554d6fee6"
},
{
"label": "world_class_operator_runbook",
"path": "reports/world_class_operator_runbook.json",
"exists": true,
"bytes": 23957,
"sha256": "b4640688026ef9199e96f80bd2d9971aaca3ec6d092d8ecd052a5debc0aa94c7"
"bytes": 24021,
"sha256": "f5ca32d5ea8bae74fccd5a574d6bbd3cad46d0950b73d522e66b0a439a433860"
},
{
"label": "world_class_operator_runbook_markdown",
"path": "reports/world_class_operator_runbook.md",
"exists": true,
"bytes": 15025,
"sha256": "3a916ac568377d8df7d612426f7358283eddfa2ab5fedb7ed12db0097a8b3c48"
"bytes": 15080,
"sha256": "260d5e03c52edefd8640c2bb2a0d8ee2c4f6d4e964f925128d4ffdd5563db4ec"
},
{
"label": "world_class_operator_runbook_html",
"path": "reports/world_class_operator_runbook.html",
"exists": true,
"bytes": 20969,
"sha256": "886b915da0f27fb46f4d8cebb6211ab5066a9fd44e1ec2e3206487d9a8abfff2"
"bytes": 21030,
"sha256": "04cc091b113f018072d07a1d71ad142773c415a49e633493689903e7b399b5e6"
},
{
"label": "world_class_claim_guard",
"path": "reports/world_class_claim_guard.json",
"exists": true,
"bytes": 18218,
"sha256": "926bf86d54c2c3d09078e9cff5821e170c9fc398723d9c99bd89cdcf60e29691"
"sha256": "7359ad2ef09dc0863014aab541a92a1f3e55f18f0c0446816c1c7333cba256e9"
}
],
"missing_artifacts": [],
reports/benchmark_reproducibility.md
+29 -28
View File
@@ -1,29 +1,29 @@
# Benchmark Reproducibility
Generated at: `2026-06-16`
Commit: `3ea32f51a55aec572e423c7c0d3f66edf8f64bd0`
Working tree dirty at generation: `false`
Evidence bundle SHA256: `3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4`
Commit: `3677dd4664b0777391fb82ab9987a7b6ea975af5`
Working tree dirty at generation: `true`
Evidence bundle SHA256: `8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c`
## Summary
- reproducibility ready: `true`
- release lock ready: `true`
- release lock ready: `false`
- methodology complete: `true`
- required artifacts: `25`
- missing artifacts: `0`
- source contract sha256: `b6abceeea0f2`
- archive sha256: `7e55b9259f9a`
- source contract sha256: `7de584946cac`
- archive sha256: `1d4626e5f8a2`
- output cases: `5`
- disclosed failure cases: `3`
- reproduction commands: `23`
- provider evidence complete: `false`
- human review complete: `false`
- world-class ready: `false`
- world-class source checks: `7` pass / `13` total; `6` blocked
- world-class source checks: `6` pass / `13` total; `7` blocked
- public claim ready: `false`
- public claim blockers: `4`
- changed files at generation: `0`
- public claim blockers: `5`
- changed files at generation: `69`
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
@@ -35,22 +35,23 @@ This report proves local benchmark reproducibility only. It keeps external provi
| Blocker |
| --- |
| release lock is not clean or commit is unavailable |
| provider-backed model holdout evidence is incomplete |
| human blind-review adjudication is incomplete |
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
| world-class source checks are not all accepted (7/13 pass, 6 blocked) |
| world-class source checks are not all accepted (6/13 pass, 7 blocked) |
## Release Lock
- ready: `true`
- reason: clean generation-time HEAD
- ready: `false`
- reason: working tree was dirty at generation time
- status scope: generation-time status before this report is written
## Evidence Bundle
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `25` / `25`
- sha256: `3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4`
- sha256: `8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c`
## Methodology Sections
@@ -72,26 +73,26 @@ This report proves local benchmark reproducibility only. It keeps external provi
| output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` |
| output_schema | `evals/output/schema.json` | present | `8ee340c95064` |
| output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` |
| output_execution | `reports/output_execution_runs.json` | present | `f9487c444b2f` |
| output_execution | `reports/output_execution_runs.json` | present | `c1f94258e640` |
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
| review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` |
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
| trust_report | `reports/security_trust_report.json` | present | `ba3b69b8eb33` |
| python_compatibility | `reports/python_compatibility.json` | present | `01aa970d0d21` |
| registry_audit | `reports/registry_audit.json` | present | `979fb0ac2207` |
| package_verification | `reports/package_verification.json` | present | `e46eaa920aca` |
| install_simulation | `reports/install_simulation.json` | present | `4d071571c537` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `f881e979b36e` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `b408af112c78` |
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `63d7aaedf725` |
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `2fbecc603d8d` |
| trust_report | `reports/security_trust_report.json` | present | `47c789ac5ff9` |
| python_compatibility | `reports/python_compatibility.json` | present | `9392cf6f3c90` |
| registry_audit | `reports/registry_audit.json` | present | `462d39d38d11` |
| package_verification | `reports/package_verification.json` | present | `bd6b8467def5` |
| install_simulation | `reports/install_simulation.json` | present | `1ad04c50c23f` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `e7d9819e12a7` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `76a3f8e2b12b` |
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `1cb74eaa978b` |
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `99a0ba234d59` |
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `412186c14ddd` |
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `ab20b288f47f` |
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `b4640688026e` |
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `3a916ac56837` |
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `886b915da0f2` |
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `926bf86d54c2` |
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `b8317119e9cd` |
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `f5ca32d5ea8b` |
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `260d5e03c52e` |
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `04cc091b113f` |
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `7359ad2ef09d` |
## Reproduction Commands
reports/compiled_targets.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"target_count": 5,
reports/context_budget.json
+15 -15
View File
@@ -5,22 +5,22 @@
"stats": {
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 767,
"other_text_tokens": 1001355,
"estimated_initial_load_tokens": 960,
"estimated_total_text_tokens": 1002122,
"deferred_resource_tokens": 461032,
"skill_body_tokens": 797,
"other_text_tokens": 1007838,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1008635,
"deferred_resource_tokens": 464021,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 411821,
"file_count": 115
"estimated_tokens": 414241,
"file_count": 116
},
{
"path": "references",
"estimated_tokens": 27376,
"file_count": 34
"estimated_tokens": 27945,
"file_count": 35
},
{
"path": "evals",
@@ -31,8 +31,8 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 411821,
"file_count": 115
"estimated_tokens": 414241,
"file_count": 116
}
],
"deferred_resource_governance": {
@@ -54,16 +54,16 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 411821,
"file_count": 115,
"estimated_tokens": 414241,
"file_count": 116,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
],
"summary": "Large deferred resources are indexed and backed by evidence."
},
"relevant_file_count": 570,
"relevant_file_count": 609,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 135.4
"quality_density": 131.3
}
}
reports/context_budget.md
+1 -1
View File
@@ -2,7 +2,7 @@
| Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
| --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
| root | `.` | `production` | 1000 | 960 | 767 | 461032 | `governed` | scripts:411821 | 135.4 | - | ok |
| root | `.` | `production` | 1000 | 990 | 797 | 464021 | `governed` | scripts:414241 | 131.3 | - | ok |
| complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok |
| governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok |
reports/context_budget_summary.json
+8 -8
View File
@@ -6,14 +6,14 @@
"path": ".",
"budget_tier": "production",
"budget_limit": 1000,
"initial_tokens": 960,
"skill_body_tokens": 767,
"deferred_resource_tokens": 461032,
"initial_tokens": 990,
"skill_body_tokens": 797,
"deferred_resource_tokens": 464021,
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 411821,
"file_count": 115
"estimated_tokens": 414241,
"file_count": 116
}
],
"deferred_resource_governance": {
@@ -35,14 +35,14 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 411821,
"file_count": 115,
"estimated_tokens": 414241,
"file_count": 116,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
],
"summary": "Large deferred resources are indexed and backed by evidence."
},
"quality_density": 135.4,
"quality_density": 131.3,
"unused_resource_dirs": [],
"ok": true,
"warnings": []
reports/evidence_consistency.json
+110 -108
View File
@@ -184,12 +184,12 @@
"status": "pass",
"expected": {
"status": "pass",
"detail": "initial load 960/1000; deferred 461032/120000; top deferred scripts 411821; resource governance governed; quality density 135.4",
"detail": "initial load 990/1000; deferred 464021/120000; top deferred scripts 414241; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"actual": {
"status": "pass",
"detail": "initial load 960/1000; deferred 461032/120000; top deferred scripts 411821; resource governance governed; quality density 135.4",
"detail": "initial load 990/1000; deferred 464021/120000; top deferred scripts 414241; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"paths": [
@@ -202,8 +202,8 @@
"key": "benchmark-release-lock-self-consistency",
"label": "Benchmark release lock matches git dirty state",
"status": "pass",
"expected": true,
"actual": true,
"expected": false,
"actual": false,
"paths": [
"reports/benchmark_reproducibility.json"
],
@@ -243,8 +243,8 @@
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
"expected": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0",
"actual": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0",
"expected": "3677dd4664b0777391fb82ab9987a7b6ea975af5",
"actual": "3677dd4664b0777391fb82ab9987a7b6ea975af5",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
@@ -256,30 +256,30 @@
"label": "overview embeds benchmark summary fields",
"status": "pass",
"expected": {
"release_lock_ready": true,
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
"world_class_source_blocked_count": 6,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"actual": {
"release_lock_ready": true,
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
"world_class_source_blocked_count": 6,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"paths": [
"reports/benchmark_reproducibility.json",
@@ -293,13 +293,13 @@
"status": "pass",
"expected": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"source_types": {
"manual": 1
@@ -307,13 +307,13 @@
},
"actual": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"source_types": {
"manual": 1
@@ -336,8 +336,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
@@ -348,8 +348,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
@@ -369,7 +369,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 13,
"source_pass_count": 7
"source_pass_count": 6
},
"actual": {
"ready": false,
@@ -377,7 +377,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 13,
"source_pass_count": 7
"source_pass_count": 6
},
"paths": [
"reports/world_class_evidence_ledger.json",
@@ -389,8 +389,8 @@
"key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit",
"status": "pass",
"expected": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0",
"actual": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0",
"expected": "3677dd4664b0777391fb82ab9987a7b6ea975af5",
"actual": "3677dd4664b0777391fb82ab9987a7b6ea975af5",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
@@ -402,30 +402,30 @@
"label": "interpretation embeds benchmark summary fields",
"status": "pass",
"expected": {
"release_lock_ready": true,
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
"world_class_source_blocked_count": 6,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"actual": {
"release_lock_ready": true,
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
"world_class_source_blocked_count": 6,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"paths": [
"reports/benchmark_reproducibility.json",
@@ -439,13 +439,13 @@
"status": "pass",
"expected": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"source_types": {
"manual": 1
@@ -453,13 +453,13 @@
},
"actual": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"source_types": {
"manual": 1
@@ -482,8 +482,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
@@ -494,8 +494,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
@@ -515,7 +515,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 13,
"source_pass_count": 7
"source_pass_count": 6
},
"actual": {
"ready": false,
@@ -523,7 +523,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 13,
"source_pass_count": 7
"source_pass_count": 6
},
"paths": [
"reports/world_class_evidence_ledger.json",
@@ -572,7 +572,7 @@
"label": "可维护性",
"score": 100,
"reasons": [
"SKILL.md 约 356 个词/字。",
"SKILL.md 约 360 个词/字。",
"入口文件保持克制，可维护性较好。",
"references/ 已承载扩展指导。",
"scripts/ 已承载确定性逻辑。",
@@ -593,7 +593,7 @@
"label": "上下文成本",
"score": 42,
"reasons": [
"入口约 356 个词/字，references 约 16388 个词/字。",
"入口约 360 个词/字，references 约 16740 个词/字。",
"分数越高代表上下文成本越低。",
"上下文成本偏高，建议压缩入口或拆分 references。"
]
@@ -636,7 +636,7 @@
"label": "可维护性",
"score": 100,
"reasons": [
"SKILL.md 约 356 个词/字。",
"SKILL.md 约 360 个词/字。",
"入口文件保持克制，可维护性较好。",
"references/ 已承载扩展指导。",
"scripts/ 已承载确定性逻辑。",
@@ -657,7 +657,7 @@
"label": "上下文成本",
"score": 42,
"reasons": [
"入口约 356 个词/字，references 约 16388 个词/字。",
"入口约 360 个词/字，references 约 16740 个词/字。",
"分数越高代表上下文成本越低。",
"上下文成本偏高，建议压缩入口或拆分 references。"
]
@@ -889,7 +889,7 @@
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
],
"gaps": [
"上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。"
"上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。"
],
"recommendations": [
"先改触发边界，再扩展工作流。",
@@ -937,7 +937,7 @@
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
],
"gaps": [
"上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。"
"上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。"
],
"recommendations": [
"先改触发边界，再扩展工作流。",
@@ -1012,7 +1012,7 @@
"name": "包体膨胀风险",
"impact": 2,
"probability": 1,
"signal": "SKILL.md 约 356 个词/字。",
"signal": "SKILL.md 约 360 个词/字。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
@@ -1171,7 +1171,7 @@
"name": "包体膨胀风险",
"impact": 2,
"probability": 1,
"signal": "SKILL.md 约 356 个词/字。",
"signal": "SKILL.md 约 360 个词/字。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
@@ -1322,7 +1322,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 13,
"source_pass_count": 7,
"source_pass_count": 6,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -1381,7 +1381,8 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events"
"External events",
"Adoption sample"
]
}
]
@@ -1395,7 +1396,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 13,
"source_pass_count": 7,
"source_pass_count": 6,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -1454,7 +1455,8 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events"
"External events",
"Adoption sample"
]
}
]
@@ -1499,13 +1501,13 @@
"path": "references",
"label": "Extended guidance and reusable notes",
"kind": "folder",
"file_count": 34
"file_count": 35
},
{
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 115
"file_count": 116
},
{
"path": "evals",
@@ -1517,10 +1519,10 @@
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 227
"file_count": 229
}
],
"file_count": 409,
"file_count": 413,
"folder_count": 4,
"distribution": [
{
@@ -1541,11 +1543,11 @@
},
{
"label": "references",
"value": 34
"value": 35
},
{
"label": "scripts",
"value": 115
"value": 116
},
{
"label": "evals",
@@ -1553,7 +1555,7 @@
},
{
"label": "reports",
"value": 227
"value": 229
}
]
},
@@ -1587,13 +1589,13 @@
"path": "references",
"label": "Extended guidance and reusable notes",
"kind": "folder",
"file_count": 34
"file_count": 35
},
{
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 115
"file_count": 116
},
{
"path": "evals",
@@ -1605,10 +1607,10 @@
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 227
"file_count": 229
}
],
"file_count": 409,
"file_count": 413,
"folder_count": 4,
"distribution": [
{
@@ -1629,11 +1631,11 @@
},
{
"label": "references",
"value": 34
"value": 35
},
{
"label": "scripts",
"value": 115
"value": 116
},
{
"label": "evals",
@@ -1641,7 +1643,7 @@
},
{
"label": "reports",
"value": 227
"value": 229
}
]
},
@@ -1804,15 +1806,15 @@
"expected": {
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
"world_class_source_blocked_count": 6,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false
},
"actual": {
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
"world_class_source_blocked_count": 6,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false
},
"paths": [
@@ -1828,8 +1830,8 @@
"expected": {
"pending_count": 4,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"preflight_counts_as_evidence": false,
"credential_value_exposed": false
@@ -1837,8 +1839,8 @@
"actual": {
"pending_count": 4,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"preflight_counts_as_evidence": false,
"credential_value_exposed": false
@@ -1972,8 +1974,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"plan_keys": [
"human-adjudication",
"native-client-telemetry",
@@ -2121,8 +2123,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"plan_keys": [
"human-adjudication",
"native-client-telemetry",
@@ -2277,16 +2279,16 @@
"score `91`",
"`16` gates",
"`3` warnings",
"`31` declared internal modules",
"`84 / 84` CLI help smoke checks passing across `115` scripts",
"`630` zip entries",
"archive with `630` entries",
"`32` declared internal modules",
"`84 / 84` CLI help smoke checks passing across `116` scripts",
"`634` zip entries",
"archive with `634` entries",
"`12` installer permission checks enforced",
"`0` permission failures",
"`25` required artifacts",
"`23` reproduction commands",
"initial load `960/1000`",
"target count is `78`"
"initial load `990/1000`",
"target count is `79`"
],
"actual": "all present",
"paths": [
reports/install_simulation.json
+10 -10
View File
@@ -1,14 +1,14 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"package_dir": "tests/tmp_review_studio/dist",
"install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill",
"installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
"package_dir": "dist",
"install_root": "dist/install-simulation/simulate-yao-meta-skill",
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 630,
"archive_entry_count": 634,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -26,7 +26,7 @@
{
"id": "archive-present",
"status": "pass",
"detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip"
"detail": "Package archive exists: dist/yao-meta-skill.zip"
},
{
"id": "archive-safe-paths",
@@ -272,9 +272,9 @@
"failures": [],
"warnings": [],
"artifacts": {
"archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip",
"package_manifest": "tests/tmp_review_studio/dist/manifest.json",
"json": "tests/tmp_review_studio/install_simulation.json",
"markdown": "tests/tmp_review_studio/install_simulation.md"
"archive": "dist/yao-meta-skill.zip",
"package_manifest": "dist/manifest.json",
"json": "reports/install_simulation.json",
"markdown": "reports/install_simulation.md"
}
}
reports/install_simulation.md
+2 -2
View File
@@ -1,7 +1,7 @@
# Install Simulation
- OK: `True`
- Package directory: `tests/tmp_review_studio/dist`
- Package directory: `dist`
- Archive extracted: `True`
- Entrypoint loaded: `True`
- Manifest loaded: `True`
@@ -16,7 +16,7 @@
| Check | Status | Detail |
| --- | --- | --- |
| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip |
| `archive-present` | `pass` | Package archive exists: dist/yao-meta-skill.zip |
| `archive-safe-paths` | `pass` | Archive has no absolute or parent-traversal entries |
| `single-top-level` | `pass` | Archive top-level directory is yao-meta-skill |
| `entrypoint-load` | `pass` | Installed SKILL.md frontmatter is readable |
reports/output_execution_runs.json
+10 -10
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 45.97,
"duration_ms": 26.41,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 38.0,
"duration_ms": 26.38,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 35.96,
"duration_ms": 26.02,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 35.66,
"duration_ms": 26.01,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.56,
"duration_ms": 25.98,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.61,
"duration_ms": 26.24,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.27,
"duration_ms": 26.23,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.29,
"duration_ms": 26.52,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 34.96,
"duration_ms": 26.24,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.68,
"duration_ms": 26.24,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
reports/output_execution_runs.md
+10 -10
View File
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
| skill-package-contract | baseline | command | local-output-eval-runner | 45.97 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 38.0 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 35.96 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 35.66 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 32.56 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 31.61 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 32.27 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 32.29 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 34.96 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 31.68 | 98 | 100.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 26.41 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 26.38 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 26.02 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.01 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 25.98 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.24 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.23 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.52 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.24 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.24 | 98 | 100.0 | pass |
## Next Fixes
reports/package_verification.json
+2 -2
View File
@@ -8,8 +8,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"archive_entry_count": 630,
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"archive_entry_count": 634,
"failure_count": 0,
"warning_count": 0
},
reports/package_verification.md
+1 -1
View File
@@ -4,7 +4,7 @@
- Package directory: `dist`
- Targets: `4 / 4` adapters present
- Archive present: `True`
- Archive SHA256: `7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed`
- Archive SHA256: `1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35`
- Failures: `0`
- Warnings: `0`
reports/prompt-quality-profile.json
+7 -7
View File
@@ -1,6 +1,6 @@
{
"skill_name": "yao-meta-skill",
"relevance": "prompt-heavy",
"relevance": "prompt-aware",
"primary_task_family": {
"key": "execution_operation",
"label": "Execution operation",
@@ -46,15 +46,15 @@
"format_guidance": "Return options with rationale, selection criteria, and refinement paths."
},
{
"key": "prompt_engineering",
"label": "Prompt engineering",
"key": "analytical_reasoning",
"label": "Analytical reasoning",
"score": 1,
"matched_keywords": [
"prompt"
"decision"
],
"role_guidance": "Use a prompt engineer role only when role design materially improves execution.",
"task_guidance": "Map Role, Task, and Format into skill behavior rather than copying a large prompt template.",
"format_guidance": "Return a compact prompt contract plus tests, quality matrix, and usage notes."
"role_guidance": "Use an analyst role that separates evidence, inference, uncertainty, and recommendation.",
"task_guidance": "State assumptions, compare alternatives, and make the decision path inspectable.",
"format_guidance": "Return findings, evidence, tradeoffs, recommendation, and residual risks."
}
],
"complexity": {
reports/prompt-quality-profile.md
+6 -6
View File
@@ -1,7 +1,7 @@
# Prompt Quality Profile
Skill: `yao-meta-skill`
Relevance: `prompt-heavy`
Relevance: `prompt-aware`
Overall quality score: `89.0/100`
## Primary Task Family
@@ -74,12 +74,12 @@ Overall quality score: `89.0/100`
- Task: Generate variants, explain selection logic, and preserve the user's distinctive constraints.
- Format: Return options with rationale, selection criteria, and refinement paths.
### Prompt engineering
### Analytical reasoning
- Score: `1`
- Keywords: prompt
- Role: Use a prompt engineer role only when role design materially improves execution.
- Task: Map Role, Task, and Format into skill behavior rather than copying a large prompt template.
- Format: Return a compact prompt contract plus tests, quality matrix, and usage notes.
- Keywords: decision
- Role: Use an analyst role that separates evidence, inference, uncertainty, and recommendation.
- Task: State assumptions, compare alternatives, and make the decision path inspectable.
- Format: Return findings, evidence, tradeoffs, recommendation, and residual risks.
## Self-Repair Checks
reports/python_compatibility.json
+14 -2
View File
@@ -1,11 +1,11 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"root": ".",
"summary": {
"target_python": "3.11",
"file_count": 184,
"file_count": 186,
"issue_count": 0,
"syntax_error_count": 0,
"fstring_311_violation_count": 0,
@@ -610,6 +610,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "scripts/skillops_opportunity.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "scripts/summarize_user_signals.py",
"ok": true,
@@ -1036,6 +1042,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "tests/verify_skillops_opportunity.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "tests/verify_system_model.py",
"ok": true,
reports/python_compatibility.md
+2 -2
View File
@@ -1,12 +1,12 @@
# Python Compatibility
Generated at: `2026-06-13`
Generated at: `2026-06-16`
## Summary
- decision: `pass`
- target python: `3.11`
- files scanned: `184`
- files scanned: `186`
- issues: `0`
- syntax errors: `0`
- f-string 3.11 violations: `0`
reports/registry_audit.json
+6 -6
View File
@@ -21,8 +21,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed"
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35"
},
"compatibility": {
"openai": "pass",
@@ -53,16 +53,16 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-13"
"generated_at": "2026-06-16"
},
"index": {
"schema_version": "2.0",
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"package_count": 1,
"packages": [
{
@@ -78,7 +78,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083"
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7"
}
]
},
reports/registry_audit.md
+2 -2
View File
@@ -6,8 +6,8 @@
- Maturity: `governed`
- Owner: `Yao Team`
- License: `MIT`
- Package SHA256: `b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083`
- Archive SHA256: `7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed`
- Package SHA256: `7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7`
- Archive SHA256: `1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35`
- Install simulated: `True`
## Compatibility
reports/review-studio.html
+16 -16
View File
File diff suppressed because one or more lines are too long
reports/review-studio.json
+287 -231
View File
File diff suppressed because it is too large Load Diff
reports/review-viewer.html
+1 -1
View File
@@ -283,7 +283,7 @@
<section class="grid">
<div class="panel">
<h2>Prompt quality profile</h2>
<p class="minor">Relevance: prompt-heavy · score 89.0 / 100 · complexity expert</p>
<p class="minor">Relevance: prompt-aware · score 89.0 / 100 · complexity expert</p>
<ul><li><strong>Completeness</strong> · 100 / 100<br><span>Name missing inputs, outputs, constraints, or success standards before deepening the package.</span></li><li><strong>Clarity</strong> · 85 / 100<br><span>Replace broad verbs with observable actions and define what done means.</span></li><li><strong>Consistency</strong> · 90 / 100<br><span>Check that role, task, format, exclusions, and examples do not contradict each other.</span></li><li><strong>Practicality</strong> · 90 / 100<br><span>Add runnable steps, examples, or verification cues instead of abstract advice.</span></li><li><strong>Specificity</strong> · 80 / 100<br><span>Anchor wording in the user&#x27;s audience, domain nouns, and target outcome.</span></li></ul>
</div>
<div class="panel">
reports/review-viewer.json
+62 -61
View File
@@ -81,7 +81,7 @@
"label": "可维护性",
"score": 100,
"reasons": [
"SKILL.md 约 356 个词/字。",
"SKILL.md 约 360 个词/字。",
"入口文件保持克制，可维护性较好。",
"references/ 已承载扩展指导。",
"scripts/ 已承载确定性逻辑。",
@@ -102,7 +102,7 @@
"label": "上下文成本",
"score": 42,
"reasons": [
"入口约 356 个词/字，references 约 16388 个词/字。",
"入口约 360 个词/字，references 约 16740 个词/字。",
"分数越高代表上下文成本越低。",
"上下文成本偏高，建议压缩入口或拆分 references。"
]
@@ -206,7 +206,7 @@
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
],
"gaps": [
"上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。"
"上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。"
],
"recommendations": [
"先改触发边界，再扩展工作流。",
@@ -271,7 +271,7 @@
"name": "包体膨胀风险",
"impact": 2,
"probability": 1,
"signal": "SKILL.md 约 356 个词/字。",
"signal": "SKILL.md 约 360 个词/字。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
@@ -412,7 +412,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 13,
"source_pass_count": 7,
"source_pass_count": 6,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -471,7 +471,8 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events"
"External events",
"Adoption sample"
]
}
]
@@ -506,13 +507,13 @@
"path": "references",
"label": "Extended guidance and reusable notes",
"kind": "folder",
"file_count": 34
"file_count": 35
},
{
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 115
"file_count": 116
},
{
"path": "evals",
@@ -524,10 +525,10 @@
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 227
"file_count": 229
}
],
"file_count": 409,
"file_count": 413,
"folder_count": 4,
"distribution": [
{
@@ -548,11 +549,11 @@
},
{
"label": "references",
"value": 34
"value": 35
},
{
"label": "scripts",
"value": 115
"value": 116
},
{
"label": "evals",
@@ -560,7 +561,7 @@
},
{
"label": "reports",
"value": 227
"value": 229
}
]
},
@@ -676,13 +677,13 @@
"path": "references",
"label": "Extended guidance and reusable notes",
"kind": "folder",
"file_count": 34
"file_count": 35
},
{
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 115
"file_count": 116
},
{
"path": "evals",
@@ -694,7 +695,7 @@
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 227
"file_count": 229
}
],
"strengths": [
@@ -996,13 +997,13 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4",
"source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"evidence_bundle_sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c",
"source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1017,14 +1018,14 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
"world_class_source_blocked_count": 6,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 69
},
"commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0",
"commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -1108,9 +1109,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 202,
"script_count": 115,
"internal_module_count": 31,
"scanned_files": 204,
"script_count": 116,
"internal_module_count": 32,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1128,8 +1129,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 202,
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083"
"package_hash_file_count": 204,
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7"
},
"skill_atlas": {
"skill_count": 12,
@@ -1167,8 +1168,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed"
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35"
},
"compatibility": {
"openai": "pass",
@@ -1199,12 +1200,12 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-13"
"generated_at": "2026-06-16"
},
"failures": [],
"warnings": []
@@ -1215,8 +1216,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"archive_entry_count": 630,
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"archive_entry_count": 634,
"failure_count": 0,
"warning_count": 0
},
@@ -1227,7 +1228,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 630,
"archive_entry_count": 634,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1294,12 +1295,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed"
"to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083"
"to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7"
}
]
},
@@ -1316,14 +1317,14 @@
"ok": true,
"summary": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"edited_count": 0,
"rejected_count": 0,
"missed_count": 0,
"failed_count": 0,
"adoption_rate": 100.0,
"adoption_rate": 0,
"missed_trigger_count": 0,
"wrong_trigger_count": 0,
"bad_output_count": 0,
@@ -1332,7 +1333,7 @@
"review_overdue_count": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"failure_types": {},
"source_types": {
@@ -1554,7 +1555,7 @@
"status": "external_required",
"category": "external",
"owner": "Browser/Chrome/IDE/provider client integrator",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1606,8 +1607,8 @@
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"submitted_but_pending_count": 0,
"source_accepted_without_valid_submission_count": 0,
"overclaim_guard_active": true,
@@ -1943,7 +1944,7 @@
"status": "pending",
"source_status": "external_required",
"source_accepted": false,
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1980,7 +1981,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -2001,8 +2002,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -2018,8 +2019,8 @@
}
],
"source_check_count": 3,
"source_pass_count": 2,
"source_blocked_count": 1,
"source_pass_count": 1,
"source_blocked_count": 2,
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/native-client-telemetry.json",
@@ -14387,7 +14388,7 @@
},
"prompt_quality": {
"skill_name": "yao-meta-skill",
"relevance": "prompt-heavy",
"relevance": "prompt-aware",
"primary_task_family": {
"key": "execution_operation",
"label": "Execution operation",
@@ -14433,15 +14434,15 @@
"format_guidance": "Return options with rationale, selection criteria, and refinement paths."
},
{
"key": "prompt_engineering",
"label": "Prompt engineering",
"key": "analytical_reasoning",
"label": "Analytical reasoning",
"score": 1,
"matched_keywords": [
"prompt"
"decision"
],
"role_guidance": "Use a prompt engineer role only when role design materially improves execution.",
"task_guidance": "Map Role, Task, and Format into skill behavior rather than copying a large prompt template.",
"format_guidance": "Return a compact prompt contract plus tests, quality matrix, and usage notes."
"role_guidance": "Use an analyst role that separates evidence, inference, uncertainty, and recommendation.",
"task_guidance": "State assumptions, compare alternatives, and make the decision path inspectable.",
"format_guidance": "Return findings, evidence, tradeoffs, recommendation, and residual risks."
}
],
"complexity": {
reports/review_annotations.json
+1 -1
View File
@@ -2,7 +2,7 @@
"schema_version": "1.0",
"ok": true,
"skill_dir": ".",
"source": "tests/tmp_review_studio/empty_review_annotations_input.json",
"source": "reports/review_annotations_input.json",
"summary": {
"annotation_count": 0,
"open_count": 0,
reports/review_waivers.json
+2 -2
View File
@@ -2,7 +2,7 @@
"schema_version": "1.0",
"ok": true,
"skill_dir": ".",
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"summary": {
"waiver_count": 0,
"active_count": 0,
@@ -52,7 +52,7 @@
"Reviewer links output_review_adjudication or output_execution evidence."
],
"suggested_evidence": "reports/output_review_adjudication.md",
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md",
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md",
"world_class_boundary": "Does not count as provider, human, or public world-class completion evidence."
},
{
reports/review_waivers.md
+1 -1
View File
@@ -35,7 +35,7 @@
- waiver allowed: `true`
- risk: review pending 5; model-executed 0; output failures 0
- evidence: `reports/output_review_adjudication.md`
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md`
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md`
- world-class boundary: Does not count as provider, human, or public world-class completion evidence.
#### Required Review
reports/runtime_permission_probes.json
+5 -5
View File
@@ -2,7 +2,7 @@
"schema_version": "1.0",
"ok": true,
"skill_dir": ".",
"package_dir": "tests/tmp_review_studio/dist",
"package_dir": "dist",
"expected_capabilities": [
"file_write",
"network",
@@ -42,7 +42,7 @@
{
"target": "openai",
"status": "pass",
"adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json",
"adapter": "dist/targets/openai/adapter.json",
"permission_model": "metadata-only",
"native_enforcement": false,
"metadata_fallback_explicit": true,
@@ -139,7 +139,7 @@
{
"target": "claude",
"status": "pass",
"adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json",
"adapter": "dist/targets/claude/adapter.json",
"permission_model": "neutral-source-plus-adapter",
"native_enforcement": false,
"metadata_fallback_explicit": true,
@@ -221,7 +221,7 @@
{
"target": "generic",
"status": "pass",
"adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json",
"adapter": "dist/targets/generic/adapter.json",
"permission_model": "agent-skills-compatible-metadata",
"native_enforcement": false,
"metadata_fallback_explicit": true,
@@ -303,7 +303,7 @@
{
"target": "vscode",
"status": "pass",
"adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json",
"adapter": "dist/targets/vscode/adapter.json",
"permission_model": "vscode-workspace-trust-plus-metadata",
"native_enforcement": false,
"metadata_fallback_explicit": true,
reports/security_trust_report.json
+24 -6
View File
@@ -2,9 +2,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 202,
"script_count": 115,
"internal_module_count": 31,
"scanned_files": 204,
"script_count": 116,
"internal_module_count": 32,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -22,8 +22,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 202,
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083"
"package_hash_file_count": 204,
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7"
},
"failures": [],
"warnings": [],
@@ -1376,6 +1376,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/skillops_opportunity.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_daily_skillops_report.py to score SkillOps opportunities without writing files.",
"has_argparse": false,
"has_main_guard": false,
"uses_input": false,
"uses_network": false,
"uses_file_write": false,
"uses_subprocess": false,
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/summarize_user_signals.py",
"interface": "cli",
@@ -1691,7 +1705,7 @@
"checked_count": 84,
"passed_count": 84,
"failed_count": 0,
"skipped_count": 31,
"skipped_count": 32,
"failed_scripts": [],
"results": [
{
@@ -2616,6 +2630,10 @@
"path": "scripts/skill_report_world_class.py",
"reason": "internal module"
},
{
"path": "scripts/skillops_opportunity.py",
"reason": "internal module"
},
{
"path": "scripts/world_class_evidence_contract.py",
"reason": "internal module"
reports/security_trust_report.md
+6 -5
View File
@@ -1,9 +1,9 @@
# Security Trust Report
- OK: `True`
- Scanned files: `202`
- Scripts: `115`
- Internal script modules: `31`
- Scanned files: `204`
- Scripts: `116`
- Internal script modules: `32`
- Secret findings: `0`
- Network-capable scripts: `3`
- Network policy covered scripts: `3`
@@ -15,8 +15,8 @@
- CLI help smoke failures: `0`
- Interactive scripts: `0`
- Package hash scope: `source-contract-without-generated-reports`
- Package hash files: `202`
- Package SHA256: `b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083`
- Package hash files: `204`
- Package SHA256: `7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7`
## Failures
@@ -157,6 +157,7 @@
| scripts/skill_report_metrics.py | internal-module | True | False | False | False | False | False | False | Imported by skill_report_model.py to calculate overview report metrics. |
| scripts/skill_report_model.py | internal-module | True | False | False | False | False | False | False | Imported by render_skill_overview.py to build the v2 report data model. |
| scripts/skill_report_world_class.py | internal-module | True | False | False | False | False | False | False | Imported by skill_report_model.py to summarize world-class evidence readiness and roadmap actions. |
| scripts/skillops_opportunity.py | internal-module | True | False | False | False | False | False | False | Imported by render_daily_skillops_report.py to score SkillOps opportunities without writing files. |
| scripts/summarize_user_signals.py | cli | True | True | True | False | False | True | False | Scans an explicit local source file and summarizes redacted repeated user preference signals. |
| scripts/sync_local_install.py | cli | False | True | True | False | False | True | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/telemetry_native_host.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
reports/skill-interpretation.html
+7 -7
View File
@@ -764,7 +764,7 @@
<ul class="list"><li><span data-lang="zh-CN">把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。</span><span data-lang="en">Turn one-off experience into a reusable, evaluable, and portable skill package.</span></li><li><span data-lang="zh-CN">Skill 作者、复用团队和后续 reviewer。</span><span data-lang="en">Skill authors, reuse teams, and later reviewers.</span></li><li><span data-lang="zh-CN">创建完成后建议先打开 reports/skill-interpretation.html，再继续扩展包体。</span><span data-lang="en">After creation, open reports/skill-interpretation.html before expanding the package further.</span></li></ul>
</aside>
</div>
<div class="score-strip" aria-label="报告关键指标"><article class='score-chip'><span><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong><i style='--score:42%'></i><small><span data-lang="zh-CN">入口约 356 个词/字，references 约 16388 个词/字。</span><span data-lang="en">Entrypoint is about 356 words/characters; references are about 16388.</span></small></article></div>
<div class="score-strip" aria-label="报告关键指标"><article class='score-chip'><span><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong><i style='--score:42%'></i><small><span data-lang="zh-CN">入口约 360 个词/字，references 约 16740 个词/字。</span><span data-lang="en">Entrypoint is about 360 words/characters; references are about 16740.</span></small></article></div>
</section>
<section id="overview">
@@ -800,10 +800,10 @@
<figure class="chart-figure" data-chart="radar"><svg viewBox="0 0 300 300" role="img" aria-label="评分雷达"><text data-lang="zh-CN" x="20" y="28" class="chart-title">评分雷达</text><text data-lang="en" x="20" y="28" class="chart-title">Rating Radar</text><polygon points="150.0,127.0 171.9,142.9 163.5,168.6 136.5,168.6 128.1,142.9" fill="none" stroke="#e8e6dc" stroke-width="1"/><polygon points="150.0,104.0 193.7,135.8 177.0,187.2 123.0,187.2 106.3,135.8" fill="none" stroke="#e8e6dc" stroke-width="1"/><polygon points="150.0,81.0 215.6,128.7 190.6,205.8 109.4,205.8 84.4,128.7" fill="none" stroke="#e8e6dc" stroke-width="1"/><polygon points="150.0,58.0 237.5,121.6 204.1,224.4 95.9,224.4 62.5,121.6" fill="none" stroke="#e8e6dc" stroke-width="1"/><polygon points="150.0,58.0 237.5,121.6 204.1,224.4 95.9,224.4 62.5,121.6" fill="#E4ECF5" stroke="#1B365D" stroke-width="2"/><text data-lang="zh-CN" x="150.0" y="26.0" text-anchor="middle" dominant-baseline="middle">完整度</text><text data-lang="en" x="150.0" y="26.0" text-anchor="middle" dominant-baseline="middle">Completeness</text><text data-lang="zh-CN" x="267.9" y="111.7" text-anchor="middle" dominant-baseline="middle">触发清晰</text><text data-lang="en" x="267.9" y="111.7" text-anchor="middle" dominant-baseline="middle">Trigger clarity</text><text data-lang="zh-CN" x="222.9" y="250.3" text-anchor="middle" dominant-baseline="middle">证据充分</text><text data-lang="en" x="222.9" y="250.3" text-anchor="middle" dominant-baseline="middle">Evidence depth</text><text data-lang="zh-CN" x="77.1" y="250.3" text-anchor="middle" dominant-baseline="middle">可维护性</text><text data-lang="en" x="77.1" y="250.3" text-anchor="middle" dominant-baseline="middle">Maintainability</text><text data-lang="zh-CN" x="32.1" y="111.7" text-anchor="middle" dominant-baseline="middle">可迁移性</text><text data-lang="en" x="32.1" y="111.7" text-anchor="middle" dominant-baseline="middle">Portability</text></svg><figcaption><span data-lang="zh-CN">评分雷达展示结构完整度、触发边界、证据、维护和迁移的相对强弱。</span><span data-lang="en">The radar chart compares completeness, trigger clarity, evidence, maintainability, and portability.</span></figcaption></figure>
<article class="panel metrics-note metrics-summary-panel">
<h3><span data-lang="zh-CN">成熟度条</span><span data-lang="en">Maturity Bar</span></h3>
<ol class='metric-summary-list'><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></b><em>100</em><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></b><em>100</em><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 约 356 个词/字。</span><span data-lang="en">SKILL.md is about 356 words/characters.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></b><em>100</em><small><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">关注</span><span data-lang="en">Watch</span></span><b><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></b><em>42</em><small><span data-lang="zh-CN">入口约 356 个词/字，references 约 16388 个词/字。</span><span data-lang="en">Entrypoint is about 356 words/characters; references are about 16388.</span></small></li></ol>
<ol class='metric-summary-list'><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></b><em>100</em><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></b><em>100</em><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 约 360 个词/字。</span><span data-lang="en">SKILL.md is about 360 words/characters.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></b><em>100</em><small><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">关注</span><span data-lang="en">Watch</span></span><b><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></b><em>42</em><small><span data-lang="zh-CN">入口约 360 个词/字，references 约 16740 个词/字。</span><span data-lang="en">Entrypoint is about 360 words/characters; references are about 16740.</span></small></li></ol>
</article>
</div>
<div class="metric-grid metric-detail-grid"><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></li><li><span data-lang="zh-CN">README.md 已存在，便于人工阅读。</span><span data-lang="en">README.md exists for human-readable usage.</span></li><li><span data-lang="zh-CN">agents/interface.yaml 已存在，便于跨平台适配。</span><span data-lang="en">agents/interface.yaml exists for cross-platform adaptation.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></li><li><span data-lang="zh-CN">description 有足够长度说明任务边界。</span><span data-lang="en">The description is long enough to explain the task boundary.</span></li><li><span data-lang="zh-CN">description 已包含使用场景或排除边界信号。</span><span data-lang="en">The description includes usage-scenario or exclusion-boundary signals.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></li><li><span data-lang="zh-CN">skill-ir.json 已存在。</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></li><li><span data-lang="zh-CN">compiled_targets.json 已存在。</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 约 356 个词/字。</span><span data-lang="en">SKILL.md is about 356 words/characters.</span></li><li><span data-lang="zh-CN">入口文件保持克制，可维护性较好。</span><span data-lang="en">The entrypoint stays restrained, which supports maintainability.</span></li><li><span data-lang="zh-CN">references/ 已承载扩展指导。</span><span data-lang="en">references/ carries extended guidance.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></li><li><span data-lang="zh-CN">manifest.json 已存在。</span><span data-lang="en">manifest.json exists.</span></li><li><span data-lang="zh-CN">目标平台或 adapter target 已声明。</span><span data-lang="en">Target platforms or adapter targets are declared.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">入口约 356 个词/字，references 约 16388 个词/字。</span><span data-lang="en">Entrypoint is about 356 words/characters; references are about 16388.</span></li><li><span data-lang="zh-CN">分数越高代表上下文成本越低。</span><span data-lang="en">A higher score means lower context cost.</span></li><li><span data-lang="zh-CN">上下文成本偏高，建议压缩入口或拆分 references。</span><span data-lang="en">Context cost is high; compress the entrypoint or split references further.</span></li></ul></div></article></div>
<div class="metric-grid metric-detail-grid"><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></li><li><span data-lang="zh-CN">README.md 已存在，便于人工阅读。</span><span data-lang="en">README.md exists for human-readable usage.</span></li><li><span data-lang="zh-CN">agents/interface.yaml 已存在，便于跨平台适配。</span><span data-lang="en">agents/interface.yaml exists for cross-platform adaptation.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></li><li><span data-lang="zh-CN">description 有足够长度说明任务边界。</span><span data-lang="en">The description is long enough to explain the task boundary.</span></li><li><span data-lang="zh-CN">description 已包含使用场景或排除边界信号。</span><span data-lang="en">The description includes usage-scenario or exclusion-boundary signals.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></li><li><span data-lang="zh-CN">skill-ir.json 已存在。</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></li><li><span data-lang="zh-CN">compiled_targets.json 已存在。</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 约 360 个词/字。</span><span data-lang="en">SKILL.md is about 360 words/characters.</span></li><li><span data-lang="zh-CN">入口文件保持克制，可维护性较好。</span><span data-lang="en">The entrypoint stays restrained, which supports maintainability.</span></li><li><span data-lang="zh-CN">references/ 已承载扩展指导。</span><span data-lang="en">references/ carries extended guidance.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></li><li><span data-lang="zh-CN">manifest.json 已存在。</span><span data-lang="en">manifest.json exists.</span></li><li><span data-lang="zh-CN">目标平台或 adapter target 已声明。</span><span data-lang="en">Target platforms or adapter targets are declared.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">入口约 360 个词/字，references 约 16740 个词/字。</span><span data-lang="en">Entrypoint is about 360 words/characters; references are about 16740.</span></li><li><span data-lang="zh-CN">分数越高代表上下文成本越低。</span><span data-lang="en">A higher score means lower context cost.</span></li><li><span data-lang="zh-CN">上下文成本偏高，建议压缩入口或拆分 references。</span><span data-lang="en">Context cost is high; compress the entrypoint or split references further.</span></li></ul></div></article></div>
</div>
</div>
</section>
@@ -878,7 +878,7 @@
<div>
<table>
<thead><tr><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th><th><span data-lang="zh-CN">证据</span><span data-lang="en">Evidence</span></th><th><span data-lang="zh-CN">建议</span><span data-lang="en">Action</span></th></tr></thead>
<tbody><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">触发面保持精简，并锚定在 frontmatter description。</span><span data-lang="en">The trigger surface stays lean and anchored in the frontmatter description.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成 Skill IR，核心语义可先于平台打包被审查和迁移。</span><span data-lang="en">Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。</span><span data-lang="en">Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">缺口</span><span data-lang="en">Gap</span></td><td><span data-lang="zh-CN">上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。</span><span data-lang="en">Context cost needs improvement: Entrypoint is about 356 words/characters; references are about 16388.</span></td><td><span data-lang="zh-CN">纳入下一轮修复</span><span data-lang="en">Fix next</span></td></tr></tbody>
<tbody><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">触发面保持精简，并锚定在 frontmatter description。</span><span data-lang="en">The trigger surface stays lean and anchored in the frontmatter description.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成 Skill IR，核心语义可先于平台打包被审查和迁移。</span><span data-lang="en">Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。</span><span data-lang="en">Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">缺口</span><span data-lang="en">Gap</span></td><td><span data-lang="zh-CN">上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。</span><span data-lang="en">Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16740.</span></td><td><span data-lang="zh-CN">纳入下一轮修复</span><span data-lang="en">Fix next</span></td></tr></tbody>
</table>
<div class="two-col quality-panels">
<article class="panel">
@@ -915,11 +915,11 @@
<div>
<table>
<thead><tr><th><span data-lang="zh-CN">风险</span><span data-lang="en">Risk</span></th><th><span data-lang="zh-CN">信号</span><span data-lang="en">Signal</span></th><th><span data-lang="zh-CN">应对</span><span data-lang="en">Response</span></th></tr></thead>
<tbody><tr><td><span data-lang="zh-CN">误触发风险</span><span data-lang="en">Trigger risk</span></td><td><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">输出漂移风险</span><span data-lang="en">Output drift risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">证据不足风险</span><span data-lang="en">Evidence gap risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">包体膨胀风险</span><span data-lang="en">Package bloat risk</span></td><td><span data-lang="zh-CN">SKILL.md 约 356 个词/字。</span><span data-lang="en">SKILL.md is about 356 words/characters.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">跨平台迁移风险</span><span data-lang="en">Portability risk</span></td><td><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr></tbody>
<tbody><tr><td><span data-lang="zh-CN">误触发风险</span><span data-lang="en">Trigger risk</span></td><td><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">输出漂移风险</span><span data-lang="en">Output drift risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">证据不足风险</span><span data-lang="en">Evidence gap risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">包体膨胀风险</span><span data-lang="en">Package bloat risk</span></td><td><span data-lang="zh-CN">SKILL.md 约 360 个词/字。</span><span data-lang="en">SKILL.md is about 360 words/characters.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">跨平台迁移风险</span><span data-lang="en">Portability risk</span></td><td><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr></tbody>
</table>
</div>
</div>
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>7 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li></ul></article></div></article>
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>6 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li><li><span data-lang="zh-CN">采用样本</span><span data-lang="en">Adoption sample</span></li></ul></article></div></article>
</div>
</section>
@@ -930,7 +930,7 @@
<p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
</div>
<div class="two-col">
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-0.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-1.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-2.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="22.2 77.8" stroke-dashoffset="-2.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="75.2 24.8" stroke-dashoffset="-24.8" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">409项</text><text data-lang="en" x="130" y="136" text-anchor="middle">409 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-0.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.9" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="22.6 77.4" stroke-dashoffset="-2.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="74.8 25.2" stroke-dashoffset="-25.2" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">413项</text><text data-lang="en" x="130" y="136" text-anchor="middle">413 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
<table>
<thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
<tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
reports/skill-interpretation.json
+55 -54
View File
@@ -81,7 +81,7 @@
"label": "可维护性",
"score": 100,
"reasons": [
"SKILL.md 约 356 个词/字。",
"SKILL.md 约 360 个词/字。",
"入口文件保持克制，可维护性较好。",
"references/ 已承载扩展指导。",
"scripts/ 已承载确定性逻辑。",
@@ -102,7 +102,7 @@
"label": "上下文成本",
"score": 42,
"reasons": [
"入口约 356 个词/字，references 约 16388 个词/字。",
"入口约 360 个词/字，references 约 16740 个词/字。",
"分数越高代表上下文成本越低。",
"上下文成本偏高，建议压缩入口或拆分 references。"
]
@@ -206,7 +206,7 @@
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
],
"gaps": [
"上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。"
"上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。"
],
"recommendations": [
"先改触发边界，再扩展工作流。",
@@ -271,7 +271,7 @@
"name": "包体膨胀风险",
"impact": 2,
"probability": 1,
"signal": "SKILL.md 约 356 个词/字。",
"signal": "SKILL.md 约 360 个词/字。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
@@ -412,7 +412,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 13,
"source_pass_count": 7,
"source_pass_count": 6,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -471,7 +471,8 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events"
"External events",
"Adoption sample"
]
}
]
@@ -506,13 +507,13 @@
"path": "references",
"label": "Extended guidance and reusable notes",
"kind": "folder",
"file_count": 34
"file_count": 35
},
{
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 115
"file_count": 116
},
{
"path": "evals",
@@ -524,10 +525,10 @@
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 227
"file_count": 229
}
],
"file_count": 409,
"file_count": 413,
"folder_count": 4,
"distribution": [
{
@@ -548,11 +549,11 @@
},
{
"label": "references",
"value": 34
"value": 35
},
{
"label": "scripts",
"value": 115
"value": 116
},
{
"label": "evals",
@@ -560,7 +561,7 @@
},
{
"label": "reports",
"value": 227
"value": 229
}
]
},
@@ -680,13 +681,13 @@
"path": "references",
"label": "Extended guidance and reusable notes",
"kind": "folder",
"file_count": 34
"file_count": 35
},
{
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 115
"file_count": 116
},
{
"path": "evals",
@@ -698,7 +699,7 @@
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 227
"file_count": 229
}
],
"strengths": [
@@ -1000,13 +1001,13 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4",
"source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"evidence_bundle_sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c",
"source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1021,14 +1022,14 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
"world_class_source_blocked_count": 6,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 69
},
"commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0",
"commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -1112,9 +1113,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 202,
"script_count": 115,
"internal_module_count": 31,
"scanned_files": 204,
"script_count": 116,
"internal_module_count": 32,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1132,8 +1133,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 202,
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083"
"package_hash_file_count": 204,
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7"
},
"skill_atlas": {
"skill_count": 12,
@@ -1171,8 +1172,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed"
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35"
},
"compatibility": {
"openai": "pass",
@@ -1203,12 +1204,12 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-13"
"generated_at": "2026-06-16"
},
"failures": [],
"warnings": []
@@ -1219,8 +1220,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"archive_entry_count": 630,
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"archive_entry_count": 634,
"failure_count": 0,
"warning_count": 0
},
@@ -1231,7 +1232,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 630,
"archive_entry_count": 634,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1298,12 +1299,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed"
"to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083"
"to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7"
}
]
},
@@ -1320,14 +1321,14 @@
"ok": true,
"summary": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"edited_count": 0,
"rejected_count": 0,
"missed_count": 0,
"failed_count": 0,
"adoption_rate": 100.0,
"adoption_rate": 0,
"missed_trigger_count": 0,
"wrong_trigger_count": 0,
"bad_output_count": 0,
@@ -1336,7 +1337,7 @@
"review_overdue_count": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"failure_types": {},
"source_types": {
@@ -1558,7 +1559,7 @@
"status": "external_required",
"category": "external",
"owner": "Browser/Chrome/IDE/provider client integrator",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1610,8 +1611,8 @@
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"submitted_but_pending_count": 0,
"source_accepted_without_valid_submission_count": 0,
"overclaim_guard_active": true,
@@ -1947,7 +1948,7 @@
"status": "pending",
"source_status": "external_required",
"source_accepted": false,
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1984,7 +1985,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -2005,8 +2006,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -2022,8 +2023,8 @@
}
],
"source_check_count": 3,
"source_pass_count": 2,
"source_blocked_count": 1,
"source_pass_count": 1,
"source_blocked_count": 2,
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/native-client-telemetry.json",
reports/skill-os-2-review.md
+5 -5
View File
@@ -114,13 +114,13 @@ Next move: add real client or installer permission enforcement integration.
| Output Eval | `5` cases, with-skill pass rate `100`, baseline pass rate `0`, with file-backed, near-neighbor, boundary coverage, `10` local command-runner execution runs, `0` recorded fixture runs, `0` provider model-executed runs in root release evidence, `10` estimated token counts, provider runner v0 available, `5` blind A/B review pairs, a generated `reports/output_review_decisions.json` template, `0 / 5` reviewer decisions pending, `0` answer keys revealed, and `5` pending answers hidden |
| Runtime Conformance | `5 / 5` targets passing |
| Target Compiler | `5 / 5` compiled target contracts generated for OpenAI, Claude, generic, Agent Skills compatible, and VS Code / Copilot outputs, including target permission contracts and target-native behavior contracts |
| Trust | `0` secret findings, `1` pinned dependency file, `31` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `84 / 84` CLI help smoke checks passing across `115` scripts, source-contract hash scope explicit |
| Trust | `0` secret findings, `1` pinned dependency file, `32` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `84 / 84` CLI help smoke checks passing across `116` scripts, source-contract hash scope explicit |
| Permission Governance | `3 / 3` required high-permission capabilities approved, `0` missing, `0` invalid, `0` expired |
| Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility |
| Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility |
| Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix |
| Package Verification | `4 / 4` target adapters present, archive verified, `630` zip entries, `0` failures, `0` warnings |
| Install Simulation | archive with `630` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
| Package Verification | `4 / 4` target adapters present, archive verified, `634` zip entries, `0` failures, `0` warnings |
| Install Simulation | archive with `634` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
| Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures |
| Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes |
| Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages |
@@ -132,8 +132,8 @@ Next move: add real client or installer permission enforcement integration.
| World-Class Evidence Ledger | `4` evidence entries remain pending: `1` human-required and `3` external-required; anti-overclaim guards block planned work, metadata fallbacks, pending review, and local command runners from counting as completion |
| Benchmark Reproducibility | local reproducibility ready with `25` required artifacts, `0` missing artifacts, `23` reproduction commands, and `3` disclosed failure cases; provider and human evidence remain explicit limitations |
| IR-first Packaging | `openai`, `claude`, `generic`, and `vscode` adapters include compiler contracts, permission contracts, target-native behavior contracts, IR provenance, semantic parity checks, and install-scope notes where applicable |
| Context Budget | initial load `960/1000`, under the production budget |
| CI | `make ci-test` target count is `78` after the Daily SkillOps gate update |
| Context Budget | initial load `990/1000`, under the production budget |
| CI | `make ci-test` target count is `79` after the SkillOps opportunity scoring gate update |
## Next Highest-Leverage Moves
reports/skill-overview.html
+7 -7
View File
@@ -764,7 +764,7 @@
<ul class="list"><li><span data-lang="zh-CN">把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。</span><span data-lang="en">Turn one-off experience into a reusable, evaluable, and portable skill package.</span></li><li><span data-lang="zh-CN">Skill 作者、复用团队和后续 reviewer。</span><span data-lang="en">Skill authors, reuse teams, and later reviewers.</span></li><li><span data-lang="zh-CN">创建完成后建议先打开 reports/skill-overview.html，再继续扩展包体。</span><span data-lang="en">After creation, open reports/skill-overview.html before expanding the package further.</span></li></ul>
</aside>
</div>
<div class="score-strip" aria-label="报告关键指标"><article class='score-chip'><span><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong><i style='--score:42%'></i><small><span data-lang="zh-CN">入口约 356 个词/字，references 约 16388 个词/字。</span><span data-lang="en">Entrypoint is about 356 words/characters; references are about 16388.</span></small></article></div>
<div class="score-strip" aria-label="报告关键指标"><article class='score-chip'><span><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong><i style='--score:42%'></i><small><span data-lang="zh-CN">入口约 360 个词/字，references 约 16740 个词/字。</span><span data-lang="en">Entrypoint is about 360 words/characters; references are about 16740.</span></small></article></div>
</section>
<section id="overview">
@@ -800,10 +800,10 @@
<figure class="chart-figure" data-chart="radar"><svg viewBox="0 0 300 300" role="img" aria-label="评分雷达"><text data-lang="zh-CN" x="20" y="28" class="chart-title">评分雷达</text><text data-lang="en" x="20" y="28" class="chart-title">Rating Radar</text><polygon points="150.0,127.0 171.9,142.9 163.5,168.6 136.5,168.6 128.1,142.9" fill="none" stroke="#e8e6dc" stroke-width="1"/><polygon points="150.0,104.0 193.7,135.8 177.0,187.2 123.0,187.2 106.3,135.8" fill="none" stroke="#e8e6dc" stroke-width="1"/><polygon points="150.0,81.0 215.6,128.7 190.6,205.8 109.4,205.8 84.4,128.7" fill="none" stroke="#e8e6dc" stroke-width="1"/><polygon points="150.0,58.0 237.5,121.6 204.1,224.4 95.9,224.4 62.5,121.6" fill="none" stroke="#e8e6dc" stroke-width="1"/><polygon points="150.0,58.0 237.5,121.6 204.1,224.4 95.9,224.4 62.5,121.6" fill="#E4ECF5" stroke="#1B365D" stroke-width="2"/><text data-lang="zh-CN" x="150.0" y="26.0" text-anchor="middle" dominant-baseline="middle">完整度</text><text data-lang="en" x="150.0" y="26.0" text-anchor="middle" dominant-baseline="middle">Completeness</text><text data-lang="zh-CN" x="267.9" y="111.7" text-anchor="middle" dominant-baseline="middle">触发清晰</text><text data-lang="en" x="267.9" y="111.7" text-anchor="middle" dominant-baseline="middle">Trigger clarity</text><text data-lang="zh-CN" x="222.9" y="250.3" text-anchor="middle" dominant-baseline="middle">证据充分</text><text data-lang="en" x="222.9" y="250.3" text-anchor="middle" dominant-baseline="middle">Evidence depth</text><text data-lang="zh-CN" x="77.1" y="250.3" text-anchor="middle" dominant-baseline="middle">可维护性</text><text data-lang="en" x="77.1" y="250.3" text-anchor="middle" dominant-baseline="middle">Maintainability</text><text data-lang="zh-CN" x="32.1" y="111.7" text-anchor="middle" dominant-baseline="middle">可迁移性</text><text data-lang="en" x="32.1" y="111.7" text-anchor="middle" dominant-baseline="middle">Portability</text></svg><figcaption><span data-lang="zh-CN">评分雷达展示结构完整度、触发边界、证据、维护和迁移的相对强弱。</span><span data-lang="en">The radar chart compares completeness, trigger clarity, evidence, maintainability, and portability.</span></figcaption></figure>
<article class="panel metrics-note metrics-summary-panel">
<h3><span data-lang="zh-CN">成熟度条</span><span data-lang="en">Maturity Bar</span></h3>
<ol class='metric-summary-list'><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></b><em>100</em><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></b><em>100</em><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 约 356 个词/字。</span><span data-lang="en">SKILL.md is about 356 words/characters.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></b><em>100</em><small><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">关注</span><span data-lang="en">Watch</span></span><b><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></b><em>42</em><small><span data-lang="zh-CN">入口约 356 个词/字，references 约 16388 个词/字。</span><span data-lang="en">Entrypoint is about 356 words/characters; references are about 16388.</span></small></li></ol>
<ol class='metric-summary-list'><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></b><em>100</em><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></b><em>100</em><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 约 360 个词/字。</span><span data-lang="en">SKILL.md is about 360 words/characters.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></b><em>100</em><small><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">关注</span><span data-lang="en">Watch</span></span><b><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></b><em>42</em><small><span data-lang="zh-CN">入口约 360 个词/字，references 约 16740 个词/字。</span><span data-lang="en">Entrypoint is about 360 words/characters; references are about 16740.</span></small></li></ol>
</article>
</div>
<div class="metric-grid metric-detail-grid"><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></li><li><span data-lang="zh-CN">README.md 已存在，便于人工阅读。</span><span data-lang="en">README.md exists for human-readable usage.</span></li><li><span data-lang="zh-CN">agents/interface.yaml 已存在，便于跨平台适配。</span><span data-lang="en">agents/interface.yaml exists for cross-platform adaptation.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></li><li><span data-lang="zh-CN">description 有足够长度说明任务边界。</span><span data-lang="en">The description is long enough to explain the task boundary.</span></li><li><span data-lang="zh-CN">description 已包含使用场景或排除边界信号。</span><span data-lang="en">The description includes usage-scenario or exclusion-boundary signals.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></li><li><span data-lang="zh-CN">skill-ir.json 已存在。</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></li><li><span data-lang="zh-CN">compiled_targets.json 已存在。</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 约 356 个词/字。</span><span data-lang="en">SKILL.md is about 356 words/characters.</span></li><li><span data-lang="zh-CN">入口文件保持克制，可维护性较好。</span><span data-lang="en">The entrypoint stays restrained, which supports maintainability.</span></li><li><span data-lang="zh-CN">references/ 已承载扩展指导。</span><span data-lang="en">references/ carries extended guidance.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></li><li><span data-lang="zh-CN">manifest.json 已存在。</span><span data-lang="en">manifest.json exists.</span></li><li><span data-lang="zh-CN">目标平台或 adapter target 已声明。</span><span data-lang="en">Target platforms or adapter targets are declared.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">入口约 356 个词/字，references 约 16388 个词/字。</span><span data-lang="en">Entrypoint is about 356 words/characters; references are about 16388.</span></li><li><span data-lang="zh-CN">分数越高代表上下文成本越低。</span><span data-lang="en">A higher score means lower context cost.</span></li><li><span data-lang="zh-CN">上下文成本偏高，建议压缩入口或拆分 references。</span><span data-lang="en">Context cost is high; compress the entrypoint or split references further.</span></li></ul></div></article></div>
<div class="metric-grid metric-detail-grid"><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></li><li><span data-lang="zh-CN">README.md 已存在，便于人工阅读。</span><span data-lang="en">README.md exists for human-readable usage.</span></li><li><span data-lang="zh-CN">agents/interface.yaml 已存在，便于跨平台适配。</span><span data-lang="en">agents/interface.yaml exists for cross-platform adaptation.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></li><li><span data-lang="zh-CN">description 有足够长度说明任务边界。</span><span data-lang="en">The description is long enough to explain the task boundary.</span></li><li><span data-lang="zh-CN">description 已包含使用场景或排除边界信号。</span><span data-lang="en">The description includes usage-scenario or exclusion-boundary signals.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></li><li><span data-lang="zh-CN">skill-ir.json 已存在。</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></li><li><span data-lang="zh-CN">compiled_targets.json 已存在。</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 约 360 个词/字。</span><span data-lang="en">SKILL.md is about 360 words/characters.</span></li><li><span data-lang="zh-CN">入口文件保持克制，可维护性较好。</span><span data-lang="en">The entrypoint stays restrained, which supports maintainability.</span></li><li><span data-lang="zh-CN">references/ 已承载扩展指导。</span><span data-lang="en">references/ carries extended guidance.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></li><li><span data-lang="zh-CN">manifest.json 已存在。</span><span data-lang="en">manifest.json exists.</span></li><li><span data-lang="zh-CN">目标平台或 adapter target 已声明。</span><span data-lang="en">Target platforms or adapter targets are declared.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">入口约 360 个词/字，references 约 16740 个词/字。</span><span data-lang="en">Entrypoint is about 360 words/characters; references are about 16740.</span></li><li><span data-lang="zh-CN">分数越高代表上下文成本越低。</span><span data-lang="en">A higher score means lower context cost.</span></li><li><span data-lang="zh-CN">上下文成本偏高，建议压缩入口或拆分 references。</span><span data-lang="en">Context cost is high; compress the entrypoint or split references further.</span></li></ul></div></article></div>
</div>
</div>
</section>
@@ -878,7 +878,7 @@
<div>
<table>
<thead><tr><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th><th><span data-lang="zh-CN">证据</span><span data-lang="en">Evidence</span></th><th><span data-lang="zh-CN">建议</span><span data-lang="en">Action</span></th></tr></thead>
<tbody><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">触发面保持精简，并锚定在 frontmatter description。</span><span data-lang="en">The trigger surface stays lean and anchored in the frontmatter description.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成 Skill IR，核心语义可先于平台打包被审查和迁移。</span><span data-lang="en">Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。</span><span data-lang="en">Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">缺口</span><span data-lang="en">Gap</span></td><td><span data-lang="zh-CN">上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。</span><span data-lang="en">Context cost needs improvement: Entrypoint is about 356 words/characters; references are about 16388.</span></td><td><span data-lang="zh-CN">纳入下一轮修复</span><span data-lang="en">Fix next</span></td></tr></tbody>
<tbody><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">触发面保持精简，并锚定在 frontmatter description。</span><span data-lang="en">The trigger surface stays lean and anchored in the frontmatter description.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成 Skill IR，核心语义可先于平台打包被审查和迁移。</span><span data-lang="en">Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。</span><span data-lang="en">Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">缺口</span><span data-lang="en">Gap</span></td><td><span data-lang="zh-CN">上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。</span><span data-lang="en">Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16740.</span></td><td><span data-lang="zh-CN">纳入下一轮修复</span><span data-lang="en">Fix next</span></td></tr></tbody>
</table>
<div class="two-col quality-panels">
<article class="panel">
@@ -915,11 +915,11 @@
<div>
<table>
<thead><tr><th><span data-lang="zh-CN">风险</span><span data-lang="en">Risk</span></th><th><span data-lang="zh-CN">信号</span><span data-lang="en">Signal</span></th><th><span data-lang="zh-CN">应对</span><span data-lang="en">Response</span></th></tr></thead>
<tbody><tr><td><span data-lang="zh-CN">误触发风险</span><span data-lang="en">Trigger risk</span></td><td><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">输出漂移风险</span><span data-lang="en">Output drift risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">证据不足风险</span><span data-lang="en">Evidence gap risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">包体膨胀风险</span><span data-lang="en">Package bloat risk</span></td><td><span data-lang="zh-CN">SKILL.md 约 356 个词/字。</span><span data-lang="en">SKILL.md is about 356 words/characters.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">跨平台迁移风险</span><span data-lang="en">Portability risk</span></td><td><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr></tbody>
<tbody><tr><td><span data-lang="zh-CN">误触发风险</span><span data-lang="en">Trigger risk</span></td><td><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">输出漂移风险</span><span data-lang="en">Output drift risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">证据不足风险</span><span data-lang="en">Evidence gap risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">包体膨胀风险</span><span data-lang="en">Package bloat risk</span></td><td><span data-lang="zh-CN">SKILL.md 约 360 个词/字。</span><span data-lang="en">SKILL.md is about 360 words/characters.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">跨平台迁移风险</span><span data-lang="en">Portability risk</span></td><td><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr></tbody>
</table>
</div>
</div>
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>7 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li></ul></article></div></article>
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>6 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li><li><span data-lang="zh-CN">采用样本</span><span data-lang="en">Adoption sample</span></li></ul></article></div></article>
</div>
</section>
@@ -930,7 +930,7 @@
<p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
</div>
<div class="two-col">
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-0.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-1.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-2.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="22.2 77.8" stroke-dashoffset="-2.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="75.2 24.8" stroke-dashoffset="-24.8" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">409项</text><text data-lang="en" x="130" y="136" text-anchor="middle">409 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-0.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.9" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="22.6 77.4" stroke-dashoffset="-2.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="74.8 25.2" stroke-dashoffset="-25.2" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">413项</text><text data-lang="en" x="130" y="136" text-anchor="middle">413 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
<table>
<thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
<tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
reports/skill-overview.json
+55 -54
View File
@@ -80,7 +80,7 @@
"label": "可维护性",
"score": 100,
"reasons": [
"SKILL.md 约 356 个词/字。",
"SKILL.md 约 360 个词/字。",
"入口文件保持克制，可维护性较好。",
"references/ 已承载扩展指导。",
"scripts/ 已承载确定性逻辑。",
@@ -101,7 +101,7 @@
"label": "上下文成本",
"score": 42,
"reasons": [
"入口约 356 个词/字，references 约 16388 个词/字。",
"入口约 360 个词/字，references 约 16740 个词/字。",
"分数越高代表上下文成本越低。",
"上下文成本偏高，建议压缩入口或拆分 references。"
]
@@ -205,7 +205,7 @@
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
],
"gaps": [
"上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。"
"上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。"
],
"recommendations": [
"先改触发边界，再扩展工作流。",
@@ -270,7 +270,7 @@
"name": "包体膨胀风险",
"impact": 2,
"probability": 1,
"signal": "SKILL.md 约 356 个词/字。",
"signal": "SKILL.md 约 360 个词/字。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
@@ -411,7 +411,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 13,
"source_pass_count": 7,
"source_pass_count": 6,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -470,7 +470,8 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events"
"External events",
"Adoption sample"
]
}
]
@@ -505,13 +506,13 @@
"path": "references",
"label": "Extended guidance and reusable notes",
"kind": "folder",
"file_count": 34
"file_count": 35
},
{
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 115
"file_count": 116
},
{
"path": "evals",
@@ -523,10 +524,10 @@
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 227
"file_count": 229
}
],
"file_count": 409,
"file_count": 413,
"folder_count": 4,
"distribution": [
{
@@ -547,11 +548,11 @@
},
{
"label": "references",
"value": 34
"value": 35
},
{
"label": "scripts",
"value": 115
"value": 116
},
{
"label": "evals",
@@ -559,7 +560,7 @@
},
{
"label": "reports",
"value": 227
"value": 229
}
]
},
@@ -675,13 +676,13 @@
"path": "references",
"label": "Extended guidance and reusable notes",
"kind": "folder",
"file_count": 34
"file_count": 35
},
{
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 115
"file_count": 116
},
{
"path": "evals",
@@ -693,7 +694,7 @@
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 227
"file_count": 229
}
],
"strengths": [
@@ -995,13 +996,13 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4",
"source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"evidence_bundle_sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c",
"source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1016,14 +1017,14 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
"world_class_source_blocked_count": 6,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 69
},
"commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0",
"commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -1107,9 +1108,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 202,
"script_count": 115,
"internal_module_count": 31,
"scanned_files": 204,
"script_count": 116,
"internal_module_count": 32,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1127,8 +1128,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 202,
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083"
"package_hash_file_count": 204,
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7"
},
"skill_atlas": {
"skill_count": 12,
@@ -1166,8 +1167,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083",
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed"
"package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35"
},
"compatibility": {
"openai": "pass",
@@ -1198,12 +1199,12 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-13"
"generated_at": "2026-06-16"
},
"failures": [],
"warnings": []
@@ -1214,8 +1215,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed",
"archive_entry_count": 630,
"archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35",
"archive_entry_count": 634,
"failure_count": 0,
"warning_count": 0
},
@@ -1226,7 +1227,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 630,
"archive_entry_count": 634,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1293,12 +1294,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed"
"to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083"
"to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7"
}
]
},
@@ -1315,14 +1316,14 @@
"ok": true,
"summary": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"edited_count": 0,
"rejected_count": 0,
"missed_count": 0,
"failed_count": 0,
"adoption_rate": 100.0,
"adoption_rate": 0,
"missed_trigger_count": 0,
"wrong_trigger_count": 0,
"bad_output_count": 0,
@@ -1331,7 +1332,7 @@
"review_overdue_count": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"failure_types": {},
"source_types": {
@@ -1553,7 +1554,7 @@
"status": "external_required",
"category": "external",
"owner": "Browser/Chrome/IDE/provider client integrator",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1605,8 +1606,8 @@
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"submitted_but_pending_count": 0,
"source_accepted_without_valid_submission_count": 0,
"overclaim_guard_active": true,
@@ -1942,7 +1943,7 @@
"status": "pending",
"source_status": "external_required",
"source_accepted": false,
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1979,7 +1980,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -2000,8 +2001,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -2017,8 +2018,8 @@
}
],
"source_check_count": 3,
"source_pass_count": 2,
"source_blocked_count": 1,
"source_pass_count": 1,
"source_blocked_count": 2,
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/native-client-telemetry.json",
reports/skill_atlas.json
+6 -4
View File
@@ -44,7 +44,7 @@
},
"catalog": {
"workspace_root": ".",
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skills": [
{
"name": "yao-meta-skill",
@@ -159,6 +159,7 @@
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/skill_report_world_class.py",
"scripts/skillops_opportunity.py",
"scripts/summarize_user_signals.py",
"scripts/sync_local_install.py",
"scripts/telemetry_native_host.py",
@@ -209,6 +210,7 @@
"references/skill-atlas-method.md",
"references/skill-engineering-method.md",
"references/skill-ir-method.md",
"references/skillops-decision-policy.md",
"references/systems-thinking-doctrine.md",
"references/telemetry-drift-method.md",
"references/trust-security-method.md",
@@ -244,8 +246,8 @@
"report": "reports/adoption_drift_report.json",
"risk_band": "low",
"event_count": 1,
"adoption_sample_count": 1,
"adoption_rate": 100.0,
"adoption_sample_count": 0,
"adoption_rate": 0,
"candidate_count": 0
}
},
@@ -908,7 +910,7 @@
"name": "incident-command-governor",
"path": "examples/governed-incident-command/generated-skill",
"reason": "review overdue by cadence monthly",
"age_days": 74,
"age_days": 77,
"allowed_days": 31,
"actionable": false,
"scope": "example"
reports/skill_os2_audit.json
+5 -5
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"item_count": 15,
@@ -197,7 +197,7 @@
"key": "trust-security",
"label": "Trust Security",
"status": "pass",
"current": "secrets 0; scripts 115; help failures 0",
"current": "secrets 0; scripts 116; help failures 0",
"target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable",
"evidence": [
{
@@ -285,7 +285,7 @@
"key": "registry-distribution",
"label": "Registry Distribution",
"status": "pass",
"current": "zip entries 630; install failures 0; permission failures 0",
"current": "zip entries 634; install failures 0; permission failures 0",
"target": "Package metadata, archive checksum, package verification, and install simulation pass",
"evidence": [
{
@@ -351,7 +351,7 @@
"key": "native-client-telemetry",
"label": "Native Client Telemetry",
"status": "external_required",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"target": "A real Browser/Chrome/provider client sends production metadata events",
"evidence": [
{
@@ -433,7 +433,7 @@
"key": "native-client-telemetry",
"label": "Native Client Telemetry",
"status": "external_required",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"target": "A real Browser/Chrome/provider client sends production metadata events",
"evidence": [
{
reports/skill_os2_audit.md
+4 -4
View File
@@ -1,6 +1,6 @@
# Skill OS 2.0 Audit
Generated at: `2026-06-13`
Generated at: `2026-06-16`
## Summary
@@ -23,14 +23,14 @@ Generated at: `2026-06-13`
| Human Adjudication | human-required | 0/5 decisions; pending 5 | Real reviewer decisions recorded before claiming output review completion | Record real A/B choices in the decision template, then regenerate adjudication. |
| Benchmark Reproducibility | pass | artifacts 25; missing 0; failures 3 | Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable | Keep the manifest current with every benchmark, package, and release evidence change. |
| Runtime Conformance | pass | 5/5 targets pass | Target package structure, metadata, relative paths, and degradation notes pass | Keep target conformance fixtures updated as platform contracts change. |
| Trust Security | pass | secrets 0; scripts 115; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. |
| Trust Security | pass | secrets 0; scripts 116; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. |
| Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. |
| Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
| Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. |
| Registry Distribution | pass | zip entries 630; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
| Registry Distribution | pass | zip entries 634; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
| Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. |
| Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. |
| Native Client Telemetry | external-required | external source events 0; adoption samples 1 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
| Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
## Open Highest-Leverage Gaps
reports/skill_os2_coverage.json
+3 -3
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"item_count": 21,
@@ -130,7 +130,7 @@
"label": "Trust Security",
"status": "pass",
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
"current": "115 scripts; secrets 0; help failures 0",
"current": "116 scripts; secrets 0; help failures 0",
"command": "python3 scripts/yao.py trust .",
"test": "python3 tests/verify_trust_check.py",
"evidence": [
@@ -204,7 +204,7 @@
"label": "Registry Distribution",
"status": "pass",
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
"current": "archive entries 630; install failures 0",
"current": "archive entries 634; install failures 0",
"command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .",
"test": "python3 tests/verify_registry_audit.py",
"evidence": [
reports/skill_os2_coverage.md
+3 -3
View File
@@ -1,6 +1,6 @@
# Skill OS 2.0 Blueprint Coverage
Generated at: `2026-06-13`
Generated at: `2026-06-16`
## Summary
@@ -26,9 +26,9 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
| Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` |
| Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` |
| Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` |
| Trust Security | `pass` | 115 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
| Trust Security | `pass` | 116 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
| Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` |
| Registry Distribution | `pass` | archive entries 630; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
| Registry Distribution | `pass` | archive entries 634; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
| Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` |
| Telemetry Drift | `pass` | events 1; recipes 5; risk low | `python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .` | `python3 tests/verify_telemetry_hooks.py` |
reports/skillops/daily/2026-06-16.json
+202
View File
@@ -268,6 +268,208 @@
]
}
],
"opportunity_summary": {
"opportunity_count": 5,
"top_score": 88,
"ready_for_approval_review_count": 1,
"proposal_review_count": 4,
"observe_more_evidence_count": 0,
"report_only_count": 0,
"action_type_counts": {
"patch_existing_skill": 3,
"agents_update": 1,
"add_eval": 1
},
"decision_counts": {
"ready_for_approval_review": 1,
"proposal_review": 4
}
},
"opportunities": [
{
"opportunity_id": "skillops-4ad91c18dd",
"proposal_id": "adapt-fbfe921ba5",
"pattern_id": "report_ui",
"title": "Improve report layout, visual hierarchy, and chart readability",
"opportunity_type": "artifact-quality",
"action_type": "patch_existing_skill",
"decision": "ready_for_approval_review",
"priority": "medium",
"score": 88,
"score_reasons": [
"support_count=5",
"confidence=0.95",
"risk=medium",
"target_files_present",
"verification_present",
"approval_required"
],
"policy_reason": "Repeated report layout feedback maps to existing renderer and design doctrine changes.",
"risk_level": "medium",
"requires_approval": true,
"write_allowed_without_approval": false,
"evidence_count": 5,
"target_files": [
"scripts/render_skill_overview.py",
"references/artifact-design-doctrine.md",
"tests/verify_skill_overview.py"
],
"verification_commands": [
"python3 tests/verify_skill_overview.py",
"python3 tests/verify_skill_report_charts.py"
]
},
{
"opportunity_id": "skillops-531e13c1c6",
"proposal_id": "adapt-59d219a1fb",
"pattern_id": "approval_safety",
"title": "Keep adaptive iteration approval-gated",
"opportunity_type": "governance",
"action_type": "agents_update",
"decision": "proposal_review",
"priority": "medium",
"score": 82,
"score_reasons": [
"support_count=2",
"confidence=0.79",
"risk=low",
"target_files_present",
"verification_present",
"approval_required"
],
"policy_reason": "Repeated privacy and approval signals should tighten durable operating guidance.",
"risk_level": "low",
"requires_approval": true,
"write_allowed_without_approval": false,
"evidence_count": 2,
"target_files": [
"references/user-memory-policy.md",
"references/autonomous-adaptation.md",
"schemas/adaptation-proposal.schema.json"
],
"verification_commands": [
"python3 tests/verify_adaptation_safety.py"
]
},
{
"opportunity_id": "skillops-709ef884f3",
"proposal_id": "adapt-18c7517f3d",
"pattern_id": "language_default",
"title": "Keep reports Chinese-first with optional English",
"opportunity_type": "report-experience",
"action_type": "patch_existing_skill",
"decision": "proposal_review",
"priority": "medium",
"score": 82,
"score_reasons": [
"support_count=2",
"confidence=0.79",
"risk=low",
"target_files_present",
"verification_present",
"approval_required"
],
"policy_reason": "Repeated language preferences can improve existing report templates after approval.",
"risk_level": "low",
"requires_approval": true,
"write_allowed_without_approval": false,
"evidence_count": 2,
"target_files": [
"scripts/render_skill_overview.py",
"references/artifact-design-doctrine.md"
],
"verification_commands": [
"python3 tests/verify_skill_overview.py"
]
},
{
"opportunity_id": "skillops-f9e43237aa",
"proposal_id": "adapt-457baca160",
"pattern_id": "delivery_format",
"title": "Make generated artifact paths explicit in CLI output",
"opportunity_type": "artifact-discoverability",
"action_type": "patch_existing_skill",
"decision": "proposal_review",
"priority": "medium",
"score": 82,
"score_reasons": [
"support_count=2",
"confidence=0.79",
"risk=low",
"target_files_present",
"verification_present",
"approval_required"
],
"policy_reason": "Repeated delivery-path requests can improve CLI and README artifact discoverability.",
"risk_level": "low",
"requires_approval": true,
"write_allowed_without_approval": false,
"evidence_count": 2,
"target_files": [
"scripts/yao.py",
"README.md"
],
"verification_commands": [
"python3 tests/verify_yao_cli.py"
]
},
{
"opportunity_id": "skillops-0a3a2de7c3",
"proposal_id": "adapt-abfee25d3a",
"pattern_id": "evidence_testing",
"title": "Attach tests and evidence refresh to each upgrade",
"opportunity_type": "quality-gate",
"action_type": "add_eval",
"decision": "proposal_review",
"priority": "medium",
"score": 74,
"score_reasons": [
"support_count=2",
"confidence=0.79",
"risk=medium",
"target_files_present",
"verification_present",
"approval_required"
],
"policy_reason": "Repeated verification and evidence requests should become focused checks.",
"risk_level": "medium",
"requires_approval": true,
"write_allowed_without_approval": false,
"evidence_count": 2,
"target_files": [
"tests/verify_adaptation_safety.py",
"scripts/render_skill_os2_coverage.py",
"reports/skill_os2_coverage.json"
],
"verification_commands": [
"python3 tests/verify_adaptation_safety.py",
"python3 tests/verify_skill_os2_coverage.py"
]
}
],
"decision_policy": {
"schema_version": "1.0",
"contract": "skillops-opportunity-scoring",
"score_range": [
0,
100
],
"score_bands": {
"85-100": "ready_for_approval_review",
"70-84": "proposal_review",
"50-69": "observe_more_evidence",
"0-49": "report_only_or_no_action"
},
"action_types": [
"add_eval",
"agents_update",
"patch_existing_skill",
"report_only"
],
"writes_source_files": false,
"auto_patch_enabled": false,
"approval_required_for_writes": true
},
"approval": {
"approval_count": 0,
"pending_review_count": 0,
reports/skillops/daily/2026-06-16.md
+46
View File
@@ -36,6 +36,52 @@ This report is an operations cockpit for explicit-source SkillOps. It does not s
- `high` Review proposal-only adaptation items before preparing any approval ledger entry.
- `high` Collect accepted external or human evidence for the pending world-class ledger entries.
## Opportunities
- count: `5`
- top score: `88`
- ready for approval review: `1`
### Improve report layout, visual hierarchy, and chart readability
- ID: `skillops-4ad91c18dd`
- Action: `patch_existing_skill`
- Decision: `ready_for_approval_review`
- Score: `88`
- Risk: `medium`
- Policy: Repeated report layout feedback maps to existing renderer and design doctrine changes.
### Keep adaptive iteration approval-gated
- ID: `skillops-531e13c1c6`
- Action: `agents_update`
- Decision: `proposal_review`
- Score: `82`
- Risk: `low`
- Policy: Repeated privacy and approval signals should tighten durable operating guidance.
### Keep reports Chinese-first with optional English
- ID: `skillops-709ef884f3`
- Action: `patch_existing_skill`
- Decision: `proposal_review`
- Score: `82`
- Risk: `low`
- Policy: Repeated language preferences can improve existing report templates after approval.
### Make generated artifact paths explicit in CLI output
- ID: `skillops-f9e43237aa`
- Action: `patch_existing_skill`
- Decision: `proposal_review`
- Score: `82`
- Risk: `low`
- Policy: Repeated delivery-path requests can improve CLI and README artifact discoverability.
### Attach tests and evidence refresh to each upgrade
- ID: `skillops-0a3a2de7c3`
- Action: `add_eval`
- Decision: `proposal_review`
- Score: `74`
- Risk: `medium`
- Policy: Repeated verification and evidence requests should become focused checks.
## Patterns
- `language_default`: Default language preference (support `2`, confidence `0.79`)
reports/upgrade_check.json
+5 -5
View File
@@ -1,7 +1,7 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"previous": {
"name": "yao-meta-skill",
"version": "1.0.0",
@@ -70,12 +70,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed"
"to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083"
"to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7"
}
]
},
@@ -90,7 +90,7 @@
"artifacts": {
"previous_package": "registry/examples/yao-meta-skill-1.0.0.json",
"current_package": "reports/registry_audit.json",
"json": "tests/tmp_review_studio/upgrade_check.json",
"markdown": "tests/tmp_review_studio/upgrade_check.md"
"json": "reports/upgrade_check.json",
"markdown": "reports/upgrade_check.md"
}
}
reports/world_class_claim_guard.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"ledger_ready_to_claim_world_class": false,
reports/world_class_claim_guard.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Claim Guard
Generated at: `2026-06-13`
Generated at: `2026-06-16`
## Summary
reports/world_class_evidence_intake.json
+2 -2
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"schema_present": true,
@@ -307,7 +307,7 @@
"source_accepted": false,
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
reports/world_class_evidence_intake.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Intake
Generated at: `2026-06-13`
Generated at: `2026-06-16`
## Summary
reports/world_class_evidence_ledger.json
+11 -11
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"decision": "evidence-pending",
"ready_to_claim_world_class": false,
@@ -15,8 +15,8 @@
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"submitted_but_pending_count": 0,
"source_accepted_without_valid_submission_count": 0,
"overclaim_guard_active": true,
@@ -31,8 +31,8 @@
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"submitted_but_pending_count": 0,
"source_accepted_without_valid_submission_count": 0,
"overclaim_guard_active": true,
@@ -393,7 +393,7 @@
"status": "pending",
"source_status": "external_required",
"source_accepted": false,
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -430,7 +430,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -451,8 +451,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -468,8 +468,8 @@
}
],
"source_check_count": 3,
"source_pass_count": 2,
"source_blocked_count": 1,
"source_pass_count": 1,
"source_blocked_count": 2,
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/native-client-telemetry.json",
reports/world_class_evidence_ledger.md
+7 -7
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Ledger
Generated at: `2026-06-13`
Generated at: `2026-06-16`
## Summary
@@ -8,8 +8,8 @@ Generated at: `2026-06-13`
- ready to claim world-class: `false`
- entries: `4`
- source accepted: `0`
- source checks: `7` pass / `13` total
- source blocked: `6`
- source checks: `6` pass / `13` total
- source blocked: `7`
- accepted: `0`
- pending: `4`
- human pending: `1`
@@ -29,7 +29,7 @@ This ledger records the current evidence state. It requires both passing source
| `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
| `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices in the decision template, then regenerate adjudication. |
| `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 1 | Install a real client against the native host and import production metadata-only events. |
| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | Install a real client against the native host and import production metadata-only events. |
## Provider Holdout
@@ -167,8 +167,8 @@ This ledger records the current evidence state. It requires both passing source
- objective: Import production metadata-only events from a real external client into the local drift loop.
- source status: `external_required`
- observed state: `{"external_source_events": 0, "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false}`
- source checks: `2` pass / `3` total
- observed state: `{"external_source_events": 0, "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false}`
- source checks: `1` pass / `3` total
- submission state: `{"status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", "artifact_ref_count": 0, "attested_real_evidence": false, "privacy_contract_satisfied": false, "ledger_counts_as_completion": false}`
### Provenance Requirements
@@ -192,7 +192,7 @@ This ledger records the current evidence state. It requires both passing source
| Check | Current | Expected | Status |
| --- | --- | --- | --- |
| External events | `0` | `>0` | `blocked` |
| Adoption sample | `1` | `>0` | `pass` |
| Adoption sample | `0` | `>0` | `blocked` |
| Raw content blocked | `False` | `false` | `pass` |
### Completion Assertions
reports/world_class_evidence_plan.json
+3 -3
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"audit_decision": "continue-iteration",
@@ -141,7 +141,7 @@
"status": "external_required",
"category": "external",
"owner": "Browser/Chrome/IDE/provider client integrator",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -299,7 +299,7 @@
"status": "external_required",
"category": "external",
"owner": "Browser/Chrome/IDE/provider client integrator",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
reports/world_class_evidence_plan.md
+2 -2
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Plan
Generated at: `2026-06-13`
Generated at: `2026-06-16`
## Summary
@@ -22,7 +22,7 @@ This report is an execution plan for the remaining world-class evidence gaps. It
| `provider-holdout` | `external_required` | `external` | operator with provider credentials | model-executed 0; token-observed 0 |
| `human-adjudication` | `human_required` | `human` | human reviewer | 0/5 decisions; pending 5 |
| `native-permission-enforcement` | `external_required` | `external` | target client or installer integrator | native-enforced targets 0; installer-enforced targets 4 |
| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 |
| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 |
## Provider Holdout
reports/world_class_evidence_preflight.html
+4 -4
View File
@@ -59,7 +59,7 @@
<span class="eyebrow">Evidence Collection</span>
<h1>World-Class Evidence Preflight</h1>
<p class="lede">This operator view shows which external and human evidence is still blocked, which commands prepare editable submission drafts, and why preflight never counts as accepted evidence.</p>
<div class="stats"><article><span>Decision</span><strong>collection-preflight-blocked</strong></article><article><span>Pending</span><strong>4</strong></article><article><span>Ready</span><strong>1</strong></article><article><span>Blocked</span><strong>3</strong></article><article><span>Source</span><strong>7/13</strong></article></div>
<div class="stats"><article><span>Decision</span><strong>collection-preflight-blocked</strong></article><article><span>Pending</span><strong>4</strong></article><article><span>Ready</span><strong>1</strong></article><article><span>Blocked</span><strong>3</strong></article><article><span>Source</span><strong>6/13</strong></article></div>
</section>
<section class="section two-col" id="handoff">
<article class="panel">
@@ -495,15 +495,15 @@
</dl>
</article>
<article class="check-row pass">
<article class="check-row blocked">
<div>
<span>adoption_sample_count</span>
<strong>Adoption sample</strong>
</div>
<dl>
<dt>Current</dt><dd><code>1</code></dd>
<dt>Current</dt><dd><code>0</code></dd>
<dt>Expected</dt><dd><code>&gt;0</code></dd>
<dt>Status</dt><dd>pass</dd>
<dt>Status</dt><dd>blocked</dd>
<dt>Action</dt><dd>Telemetry must include adoption outcome evidence.</dd>
</dl>
</article>
reports/world_class_evidence_preflight.json
+6 -6
View File
@@ -14,8 +14,8 @@
"collection_ready_count": 1,
"collection_blocked_count": 3,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"pending_count": 4,
"ready_to_claim_world_class": false,
"credential_value_exposed": false,
@@ -448,8 +448,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -768,8 +768,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
reports/world_class_evidence_preflight.md
+2 -2
View File
@@ -10,7 +10,7 @@ Generated at: `2026-06-16`
- credential value exposed: `false`
- collection ready: `1`
- collection blocked: `3`
- source checks: `7` pass / `13` total
- source checks: `6` pass / `13` total
This preflight report checks whether an operator can start collecting the remaining external or human evidence. It never accepts evidence, prints secret values, or changes the world-class ledger.
@@ -132,7 +132,7 @@ Generate the submission kit after the real provider, human, native-permission, o
| Check | Current | Expected | Status | Next action |
| --- | --- | --- | --- | --- |
| External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. |
| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. |
| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. |
| Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. |
## Boundary
reports/world_class_operator_runbook.html
+4 -4
View File
@@ -57,7 +57,7 @@
<span class="eyebrow">Evidence Operations</span>
<h1>World-Class Operator Runbook</h1>
<p class="lede">A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.</p>
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>7/13</strong></article><article><span>Blocked</span><strong>6</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>6/13</strong></article><article><span>Blocked</span><strong>7</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
</section>
<section class="section panel" id="fast-path"><h2>Fast Path</h2><ol><li>Run the real external or human work for one evidence item.</li><li>Generate and fill the matching submission draft.</li><li>Validate intake and inspect the submission review queue.</li><li>Refresh the ledger and run the claim guard before making any completion claim.</li></ol></section>
<section class="section" id="items"><h2>Evidence Items</h2><div class="item-grid"><article class="item-card awaiting-submission">
@@ -120,7 +120,7 @@
<dl>
<dt>Owner</dt><dd>Browser/Chrome/IDE/provider client integrator</dd>
<dt>Ledger</dt><dd><code>pending</code></dd>
<dt>Blocked</dt><dd><code>1</code></dd>
<dt>Blocked</dt><dd><code>2</code></dd>
<dt>Submission</dt><dd><code>evidence/world_class/submissions/native-client-telemetry.json</code></dd>
</dl>
<section class="source-panel"><h4>Source Runbook</h4><ul><li>python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://&lt;extension-id&gt;/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li><li>python3 scripts/yao.py skill-atlas --workspace-root .</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section>
@@ -130,8 +130,8 @@
<section><h4>Success Checks</h4><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></section>
<section><h4>Privacy</h4><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></section>
</div>
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check pass'><span>Adoption sample</span><code>adoption_sample_count: 1 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li><li>Telemetry must include adoption outcome evidence.</li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check blocked'><span>Adoption sample</span><code>adoption_sample_count: 0 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
</article></div></section>
<section class="section panel" id="boundary"><h2>Boundary</h2><ul><li>Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.</li><li>Valid intake means ready for submission review; ledger review still requires passing source evidence.</li><li>The world-class ledger and claim guard remain the source of truth.</li></ul></section>
</main>
reports/world_class_operator_runbook.json
+10 -9
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"evidence_item_count": 4,
@@ -12,8 +12,8 @@
"valid_packet_source_incomplete_count": 0,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"runbook_counts_as_completion": false,
"decision": "collect-evidence"
@@ -394,7 +394,7 @@
"review_state": "awaiting-submission",
"source_accepted": false,
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"execution_runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
"Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
@@ -442,7 +442,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -463,8 +463,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -479,9 +479,10 @@
"next_action": "Telemetry must stay metadata-only."
}
],
"blocked_source_check_count": 1,
"blocked_source_check_count": 2,
"next_source_actions": [
"Import at least one metadata-only event from a real client."
"Import at least one metadata-only event from a real client.",
"Telemetry must include adoption outcome evidence."
],
"submission_state": {
"status": "missing",
reports/world_class_operator_runbook.md
+5 -4
View File
@@ -1,6 +1,6 @@
# World-Class Operator Runbook
Generated at: `2026-06-13`
Generated at: `2026-06-16`
## Summary
@@ -28,7 +28,7 @@ This runbook coordinates evidence collection only. It does not accept submission
| `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials. | operator with provider credentials |
| `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Record a reviewer choice for every pair. | human reviewer |
| `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator |
| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
## Provider Holdout
@@ -239,7 +239,7 @@ This runbook coordinates evidence collection only. It does not accept submission
- objective: Import production metadata-only events from a real external client into the local drift loop.
- blocking reason: No evidence packet has been submitted for review.
- blocked source checks: `1`
- blocked source checks: `2`
- submission: `evidence/world_class/submissions/native-client-telemetry.json`
- template: `evidence/world_class/templates/native-client-telemetry.intake.json`
@@ -292,13 +292,14 @@ This runbook coordinates evidence collection only. It does not accept submission
### Next Source Actions
- Import at least one metadata-only event from a real client.
- Telemetry must include adoption outcome evidence.
### Source Evidence Snapshot
| Check | Current | Expected | Status | Next action |
| --- | --- | --- | --- | --- |
| External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. |
| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. |
| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. |
| Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. |
## Boundary
reports/world_class_submission_review.json
+10 -10
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skill_dir": ".",
"decision": "awaiting-submissions",
"ready_to_claim_world_class": false,
@@ -14,8 +14,8 @@
"unmatched_submission_count": 0,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"review_counts_submission_as_completion": false,
"summary": {
"review_item_count": 4,
@@ -27,8 +27,8 @@
"unmatched_submission_count": 0,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"review_counts_submission_as_completion": false,
"decision": "awaiting-submissions"
@@ -301,7 +301,7 @@
"intake_errors": [],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -322,8 +322,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -339,8 +339,8 @@
}
],
"source_check_count": 3,
"source_pass_count": 2,
"source_blocked_count": 1,
"source_pass_count": 1,
"source_blocked_count": 2,
"success_checks": [
"reports/adoption_drift_report.json summary.source_types.external > 0",
"reports/adoption_drift_report.json summary.adoption_sample_count > 0",
reports/world_class_submission_review.md
+2 -2
View File
@@ -1,6 +1,6 @@
# World-Class Submission Review
Generated at: `2026-06-13`
Generated at: `2026-06-16`
## Summary
@@ -138,7 +138,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
#### Source Checks
- External events: 0 / >0 => blocked
- Adoption sample: 1 / >0 => pass
- Adoption sample: 0 / >0 => blocked
- Raw content blocked: False / false => pass
#### Completion Assertions
skill_atlas/catalog.json
+5 -3
View File
@@ -1,6 +1,6 @@
{
"workspace_root": ".",
"generated_at": "2026-06-13",
"generated_at": "2026-06-16",
"skills": [
{
"name": "yao-meta-skill",
@@ -115,6 +115,7 @@
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/skill_report_world_class.py",
"scripts/skillops_opportunity.py",
"scripts/summarize_user_signals.py",
"scripts/sync_local_install.py",
"scripts/telemetry_native_host.py",
@@ -165,6 +166,7 @@
"references/skill-atlas-method.md",
"references/skill-engineering-method.md",
"references/skill-ir-method.md",
"references/skillops-decision-policy.md",
"references/systems-thinking-doctrine.md",
"references/telemetry-drift-method.md",
"references/trust-security-method.md",
@@ -200,8 +202,8 @@
"report": "reports/adoption_drift_report.json",
"risk_band": "low",
"event_count": 1,
"adoption_sample_count": 1,
"adoption_rate": 100.0,
"adoption_sample_count": 0,
"adoption_rate": 0,
"candidate_count": 0
}
},
skill_atlas/stale_skills.json
+1 -1
View File
@@ -24,7 +24,7 @@
"name": "incident-command-governor",
"path": "examples/governed-incident-command/generated-skill",
"reason": "review overdue by cadence monthly",
"age_days": 74,
"age_days": 77,
"allowed_days": 31,
"actionable": false,
"scope": "example"